Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1123. Min Range: -9.1123
Max Act: 9.1123. Min Act: -0.1700
Data Index: 8562168 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1123. Min Range: -9.1123
Max Act: 9.1123. Min Act: -0.1700
Data Index: 867244 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1123. Min Range: -9.1123
Max Act: 9.0498. Min Act: -0.1700
Data Index: 2563887 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.8623. Min Act: -0.1700
Data Index: 261656 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.7373. Min Act: -0.1700
Data Index: 6832785 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.7373. Min Act: -0.1700
Data Index: 548656 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.7373. Min Act: -0.1700
Data Index: 7203313 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.6748. Min Act: -0.1700
Data Index: 867243 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.6123. Min Act: -0.1700
Data Index: 8588469 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.6123. Min Act: -0.1700
Data Index: 4409046 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.5498. Min Act: -0.1700
Data Index: 3401546 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.4873. Min Act: -0.1700
Data Index: 6805895 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.4248. Min Act: -0.1700
Data Index: 7871616 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.4873. Min Act: -0.1700
Data Index: 7134848 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.4248. Min Act: -0.1700
Data Index: 7353058 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.3623. Min Act: -0.1700
Data Index: 8116311 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.3623. Min Act: -0.1700
Data Index: 5861367 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.2998. Min Act: -0.1700
Data Index: 1219588 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.2998. Min Act: -0.1700
Data Index: 1468907 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1123. Min Range: -9.1123
Max Act: 8.3623. Min Act: -0.1700
Data Index: 2700159 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19