Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.6777. Min Act: -0.1700
Data Index: 8590983 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.5527. Min Act: -0.1700
Data Index: 5425809 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.5527. Min Act: -0.1700
Data Index: 8355581 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.4902. Min Act: -0.1700
Data Index: 2327266 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.4902. Min Act: -0.1700
Data Index: 8543878 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.4277. Min Act: -0.1700
Data Index: 8814112 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.3652. Min Act: -0.1700
Data Index: 8298407 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.3652. Min Act: -0.1700
Data Index: 8257750 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.3027. Min Act: -0.1700
Data Index: 35315 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.3027. Min Act: -0.1700
Data Index: 2025837 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.3027. Min Act: -0.1700
Data Index: 411606 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.2402. Min Act: -0.1700
Data Index: 5498139 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.2402. Min Act: -0.1700
Data Index: 6860679 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1777. Min Act: -0.1700
Data Index: 3046583 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.2402. Min Act: -0.1700
Data Index: 6478836 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1777. Min Act: -0.1700
Data Index: 7272942 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1152. Min Act: -0.1700
Data Index: 2539031 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1152. Min Act: -0.1700
Data Index: 2007840 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1152. Min Act: -0.1700
Data Index: 8237387 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6777. Min Range: -10.6777
Max Act: 10.1152. Min Act: -0.1700
Data Index: 3854626 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19