Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.5419. Min Act: -0.1700
Data Index: 6402469 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.3382. Min Act: -0.1700
Data Index: 7335079 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.3225. Min Act: -0.1700
Data Index: 2747806 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.3068. Min Act: -0.1700
Data Index: 5901775 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.2283. Min Act: -0.1700
Data Index: 3564493 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.2440. Min Act: -0.1700
Data Index: 3863909 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.2125. Min Act: -0.1700
Data Index: 3114502 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.2440. Min Act: -0.1700
Data Index: 7489770 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.2125. Min Act: -0.1700
Data Index: 8606090 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1968. Min Act: -0.1700
Data Index: 5330226 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1654. Min Act: -0.1700
Data Index: 8434781 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1654. Min Act: -0.1700
Data Index: 6807542 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1496. Min Act: -0.1700
Data Index: 2946497 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1339. Min Act: -0.1700
Data Index: 355787 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1496. Min Act: -0.1700
Data Index: 7700610 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1339. Min Act: -0.1700
Data Index: 3785775 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1496. Min Act: -0.1700
Data Index: 4353533 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1339. Min Act: -0.1700
Data Index: 3440620 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1181. Min Act: -0.1700
Data Index: 7625883 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.1339. Min Act: -0.1700
Data Index: 1994750 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19