Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.2338. Min Act: -0.1700
Data Index: 1962969 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.1713. Min Act: -0.1700
Data Index: 3071296 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.2338. Min Act: -0.1700
Data Index: 6331346 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.1713. Min Act: -0.1700
Data Index: 2719369 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.0463. Min Act: -0.1700
Data Index: 7885401 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.1088. Min Act: -0.1700
Data Index: 1872976 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.2338. Min Range: -15.2338
Max Act: 15.0463. Min Act: -0.1700
Data Index: 4894690 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9838. Min Act: -0.1700
Data Index: 7070576 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9838. Min Act: -0.1700
Data Index: 7727076 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.7963. Min Act: -0.1700
Data Index: 6126036 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.8588. Min Act: -0.1700
Data Index: 3862544 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.8588. Min Act: -0.1700
Data Index: 7307498 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9213. Min Act: -0.1700
Data Index: 8558804 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9213. Min Act: -0.1700
Data Index: 5412200 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9838. Min Act: -0.1700
Data Index: 6065369 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.9838. Min Act: -0.1700
Data Index: 5311080 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.7963. Min Act: -0.1700
Data Index: 7880856 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.8588. Min Act: -0.1700
Data Index: 5670367 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.8588. Min Act: -0.1700
Data Index: 1372329 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.2338. Min Range: -15.2338
Max Act: 14.8588. Min Act: -0.1700
Data Index: 1428640 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19