Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3854 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.4027. Min Act: -0.1700
Data Index: 7588867 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.4027. Min Act: -0.1700
Data Index: 5325720 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3714. Min Act: -0.1700
Data Index: 2057386 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3714. Min Act: -0.1700
Data Index: 6775441 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3402. Min Act: -0.1700
Data Index: 2216160 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3402. Min Act: -0.1700
Data Index: 6742553 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3402. Min Act: -0.1700
Data Index: 1659991 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3089. Min Act: -0.1700
Data Index: 2129356 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.3089. Min Act: -0.1700
Data Index: 6659861 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 5446199 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2777. Min Act: -0.1700
Data Index: 3853566 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2777. Min Act: -0.1700
Data Index: 3484897 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 7380179 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 4426466 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 3369448 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 1011443 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2152. Min Act: -0.1700
Data Index: 6920207 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 2219224 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 293732 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4027. Min Range: -7.4027
Max Act: 7.2464. Min Act: -0.1700
Data Index: 2650241 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19