Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.8309. Min Act: -0.1700
Data Index: 3750339 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.7684. Min Act: -0.1700
Data Index: 2949244 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1108795 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.6121. Min Act: -0.1700
Data Index: 40023 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.6434. Min Act: -0.1700
Data Index: 563143 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.6434. Min Act: -0.1700
Data Index: 106203 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.6121. Min Act: -0.1700
Data Index: 8342754 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.5809. Min Act: -0.1700
Data Index: 5867580 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.5184. Min Act: -0.1700
Data Index: 1585406 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.5496. Min Act: -0.1700
Data Index: 7632529 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.4871. Min Act: -0.1700
Data Index: 4862717 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.4559. Min Act: -0.1700
Data Index: 7012248 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.4559. Min Act: -0.1700
Data Index: 3951898 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.4246. Min Act: -0.1700
Data Index: 8537772 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3934. Min Act: -0.1700
Data Index: 3977720 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3621. Min Act: -0.1700
Data Index: 3803752 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3621. Min Act: -0.1700
Data Index: 2892286 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3621. Min Act: -0.1700
Data Index: 744593 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3621. Min Act: -0.1700
Data Index: 6548301 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8309. Min Range: -5.8309
Max Act: 5.3621. Min Act: -0.1700
Data Index: 554032 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19