Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.4471. Min Act: -0.1700
Data Index: 5595842 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.4158. Min Act: -0.1700
Data Index: 6129114 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.4158. Min Act: -0.1700
Data Index: 7466307 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.3221. Min Act: -0.1700
Data Index: 8159417 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.3221. Min Act: -0.1700
Data Index: 8718203 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.3221. Min Act: -0.1700
Data Index: 341039 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.2908. Min Act: -0.1700
Data Index: 8694456 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.2908. Min Act: -0.1700
Data Index: 7927980 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.2596. Min Act: -0.1700
Data Index: 5072447 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7353299 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1971. Min Act: -0.1700
Data Index: 4627431 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1971. Min Act: -0.1700
Data Index: 320761 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1971. Min Act: -0.1700
Data Index: 8770531 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1658. Min Act: -0.1700
Data Index: 8096162 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1346. Min Act: -0.1700
Data Index: 5392928 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1658. Min Act: -0.1700
Data Index: 7376258 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1658. Min Act: -0.1700
Data Index: 4441540 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1971. Min Act: -0.1700
Data Index: 5687548 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3464140 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4471. Min Range: -5.4471
Max Act: 5.1346. Min Act: -0.1700
Data Index: 7223210 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19