Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3694 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.1398. Min Act: -0.1700
Data Index: 7183271 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0609. Min Act: -0.1700
Data Index: 6145653 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0452. Min Act: -0.1700
Data Index: 5073490 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0452. Min Act: -0.1700
Data Index: 1319778 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0294. Min Act: -0.1700
Data Index: 1200473 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0136. Min Act: -0.1700
Data Index: 4291416 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9978. Min Act: -0.1700
Data Index: 7393835 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1398. Min Range: -3.1398
Max Act: 3.0136. Min Act: -0.1700
Data Index: 1428365 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9820. Min Act: -0.1700
Data Index: 6378639 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9662. Min Act: -0.1700
Data Index: 3402956 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9978. Min Act: -0.1700
Data Index: 786858 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9503. Min Act: -0.1700
Data Index: 6252849 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9662. Min Act: -0.1700
Data Index: 4204754 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9345. Min Act: -0.1700
Data Index: 5870291 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9345. Min Act: -0.1700
Data Index: 1120026 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9345. Min Act: -0.1700
Data Index: 4242563 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.9028. Min Act: -0.1700
Data Index: 2685324 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.8869. Min Act: -0.1700
Data Index: 5317537 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.8869. Min Act: -0.1700
Data Index: 5574287 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1398. Min Range: -3.1398
Max Act: 2.8869. Min Act: -0.1700
Data Index: 1819178 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19