Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.4127. Min Act: -0.1700
Data Index: 4407228 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1314. Min Act: -0.1700
Data Index: 1532180 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.0689. Min Act: -0.1700
Data Index: 733694 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.0376. Min Act: -0.1700
Data Index: 4172324 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.0376. Min Act: -0.1700
Data Index: 1925587 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.0064. Min Act: -0.1700
Data Index: 6049497 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.9751. Min Act: -0.1700
Data Index: 3496346 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.9438. Min Act: -0.1700
Data Index: 4796362 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.9126. Min Act: -0.1700
Data Index: 5700879 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.9126. Min Act: -0.1700
Data Index: 1443000 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8813. Min Act: -0.1700
Data Index: 710485 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8813. Min Act: -0.1700
Data Index: 798974 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8500. Min Act: -0.1700
Data Index: 5917760 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8188. Min Act: -0.1700
Data Index: 3129457 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8188. Min Act: -0.1700
Data Index: 2973694 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.8031. Min Act: -0.1700
Data Index: 7318377 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.7875. Min Act: -0.1700
Data Index: 6677081 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.7719. Min Act: -0.1700
Data Index: 3177661 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.7875. Min Act: -0.1700
Data Index: 7138543 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4127. Min Range: -4.4127
Max Act: 3.7562. Min Act: -0.1700
Data Index: 3051781 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19