Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.8804. Min Act: -0.1700
Data Index: 3898356 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.6304. Min Act: -0.1700
Data Index: 7158077 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.2554. Min Act: -0.1700
Data Index: 8586149 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.2554. Min Act: -0.1700
Data Index: 4852720 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.2554. Min Act: -0.1700
Data Index: 2554756 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.3179. Min Act: -0.1700
Data Index: 3487566 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.2554. Min Act: -0.1700
Data Index: 2406255 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.1304. Min Act: -0.1700
Data Index: 8503916 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.0679. Min Act: -0.1700
Data Index: 3149776 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.0679. Min Act: -0.1700
Data Index: 4702243 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.0054. Min Act: -0.1700
Data Index: 2857641 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8804. Min Range: -10.8804
Max Act: 10.0054. Min Act: -0.1700
Data Index: 7692473 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.9429. Min Act: -0.1700
Data Index: 2369774 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8804. Min Act: -0.1700
Data Index: 5148753 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.9429. Min Act: -0.1700
Data Index: 254 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8804. Min Act: -0.1700
Data Index: 1552051 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8804. Min Act: -0.1700
Data Index: 6417041 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8179. Min Act: -0.1700
Data Index: 5751402 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8179. Min Act: -0.1700
Data Index: 8014430 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8804. Min Range: -10.8804
Max Act: 9.8179. Min Act: -0.1700
Data Index: 1989899 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19