Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.9606. Min Act: -0.1700
Data Index: 6263795 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 8068371 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.8668. Min Act: -0.1700
Data Index: 6119061 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.8668. Min Act: -0.1700
Data Index: 445492 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.8043. Min Act: -0.1700
Data Index: 2545774 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.7418. Min Act: -0.1700
Data Index: 7718719 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.6481. Min Act: -0.1700
Data Index: 8184055 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.6481. Min Act: -0.1700
Data Index: 1850004 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.6481. Min Act: -0.1700
Data Index: 7413098 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.6168. Min Act: -0.1700
Data Index: 6729814 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5856. Min Act: -0.1700
Data Index: 3618029 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5543. Min Act: -0.1700
Data Index: 6974236 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5856. Min Act: -0.1700
Data Index: 5652928 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5856. Min Act: -0.1700
Data Index: 3458533 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5543. Min Act: -0.1700
Data Index: 5458215 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5543. Min Act: -0.1700
Data Index: 1146201 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.4918. Min Act: -0.1700
Data Index: 3618030 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5231. Min Act: -0.1700
Data Index: 3281979 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5231. Min Act: -0.1700
Data Index: 4789548 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9606. Min Range: -6.9606
Max Act: 6.5231. Min Act: -0.1700
Data Index: 5592715 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19