Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.8104. Min Act: -0.1700
Data Index: 6513447 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5514362 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.7166. Min Act: -0.1700
Data Index: 7206368 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.7166. Min Act: -0.1700
Data Index: 3727626 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.6854. Min Act: -0.1700
Data Index: 2814518 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.6541. Min Act: -0.1700
Data Index: 7403796 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.6229. Min Act: -0.1700
Data Index: 5641386 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.5604. Min Act: -0.1700
Data Index: 4982562 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.5604. Min Act: -0.1700
Data Index: 349881 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.5291. Min Act: -0.1700
Data Index: 6217874 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.5291. Min Act: -0.1700
Data Index: 4793772 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.5291. Min Act: -0.1700
Data Index: 7948169 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4979. Min Act: -0.1700
Data Index: 4278447 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4979. Min Act: -0.1700
Data Index: 8291943 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4979. Min Act: -0.1700
Data Index: 5743698 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4666. Min Act: -0.1700
Data Index: 1242234 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4041. Min Act: -0.1700
Data Index: 2378148 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4041. Min Act: -0.1700
Data Index: 3494541 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4041. Min Act: -0.1700
Data Index: 873560 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8416. Min Range: -6.8416
Max Act: 6.4041. Min Act: -0.1700
Data Index: 5275359 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19