Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0303. Min Range: -10.0303
Max Act: 10.0303. Min Act: -0.1700
Data Index: 7796759 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.4678. Min Act: -0.1700
Data Index: 5759628 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.4053. Min Act: -0.1700
Data Index: 3380115 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.4053. Min Act: -0.1700
Data Index: 7832677 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.3428. Min Act: -0.1700
Data Index: 4331374 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.3428. Min Act: -0.1700
Data Index: 3637246 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.3428. Min Act: -0.1700
Data Index: 6617866 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.2803. Min Act: -0.1700
Data Index: 7812657 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.2803. Min Act: -0.1700
Data Index: 6385960 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.1553. Min Act: -0.1700
Data Index: 5483981 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.2178. Min Act: -0.1700
Data Index: 3337695 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.0928. Min Act: -0.1700
Data Index: 837287 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.0928. Min Act: -0.1700
Data Index: 5638080 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.0303. Min Act: -0.1700
Data Index: 5978456 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0303. Min Range: -10.0303
Max Act: 8.9678. Min Act: -0.1700
Data Index: 270151 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0303. Min Range: -10.0303
Max Act: 8.9678. Min Act: -0.1700
Data Index: 7222558 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0303. Min Range: -10.0303
Max Act: 8.9678. Min Act: -0.1700
Data Index: 523290 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0303. Min Range: -10.0303
Max Act: 8.9053. Min Act: -0.1700
Data Index: 1496751 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0303. Min Range: -10.0303
Max Act: 9.0303. Min Act: -0.1700
Data Index: 7684404 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0303. Min Range: -10.0303
Max Act: 8.9678. Min Act: -0.1700
Data Index: 6068392 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19