Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.4411. Min Act: -0.1700
Data Index: 612249 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.1911. Min Act: -0.1700
Data Index: 1451080 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0973. Min Act: -0.1700
Data Index: 8070322 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0661. Min Act: -0.1700
Data Index: 7847825 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0348. Min Act: -0.1700
Data Index: 1263362 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0661. Min Act: -0.1700
Data Index: 6372958 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4899842 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4411. Min Range: -7.4411
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2850645 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9723. Min Act: -0.1700
Data Index: 7976101 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9098. Min Act: -0.1700
Data Index: 6337699 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9098. Min Act: -0.1700
Data Index: 7042006 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9098. Min Act: -0.1700
Data Index: 2292736 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1882473 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1606788 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8786. Min Act: -0.1700
Data Index: 7352181 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8786. Min Act: -0.1700
Data Index: 6505362 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8473. Min Act: -0.1700
Data Index: 3353751 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8786. Min Act: -0.1700
Data Index: 5586912 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8473. Min Act: -0.1700
Data Index: 4819363 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4411. Min Range: -7.4411
Max Act: 6.8473. Min Act: -0.1700
Data Index: 3832129 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19