Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.5435. Min Act: -0.1700
Data Index: 2561321 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.3560. Min Act: -0.1700
Data Index: 8433484 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.2622. Min Act: -0.1700
Data Index: 3108081 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.2310. Min Act: -0.1700
Data Index: 4425499 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.2310. Min Act: -0.1700
Data Index: 6965265 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.2622. Min Act: -0.1700
Data Index: 5326915 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.2310. Min Act: -0.1700
Data Index: 7093597 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1685. Min Act: -0.1700
Data Index: 2592384 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3691444 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1372. Min Act: -0.1700
Data Index: 8218164 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1372. Min Act: -0.1700
Data Index: 480939 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1084889 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1372. Min Act: -0.1700
Data Index: 544812 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1060. Min Act: -0.1700
Data Index: 6765529 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0747. Min Act: -0.1700
Data Index: 834457 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0747. Min Act: -0.1700
Data Index: 5006431 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0747. Min Act: -0.1700
Data Index: 5252824 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0747. Min Act: -0.1700
Data Index: 5793823 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0435. Min Act: -0.1700
Data Index: 5158422 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0122. Min Act: -0.1700
Data Index: 6492885 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19