Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4286 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1103. Min Range: -6.1103
Max Act: 6.1103. Min Act: -0.1700
Data Index: 1184042 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9853. Min Act: -0.1700
Data Index: 5083172 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9228. Min Act: -0.1700
Data Index: 4675120 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9228. Min Act: -0.1700
Data Index: 8365579 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1235877 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8603. Min Act: -0.1700
Data Index: 7745583 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7272937 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7978. Min Act: -0.1700
Data Index: 4295679 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8291. Min Act: -0.1700
Data Index: 8573796 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7978. Min Act: -0.1700
Data Index: 4426339 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7978. Min Act: -0.1700
Data Index: 384539 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.8291. Min Act: -0.1700
Data Index: 5742079 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7978. Min Act: -0.1700
Data Index: 6974 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7666. Min Act: -0.1700
Data Index: 6484809 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7978. Min Act: -0.1700
Data Index: 7902722 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2891227 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3783628 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 7498878 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5409191 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1103. Min Range: -6.1103
Max Act: 5.7353. Min Act: -0.1700
Data Index: 729644 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19