Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.4439. Min Act: -0.1700
Data Index: 2430797 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.4439. Min Act: -0.1700
Data Index: 1300213 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.3189. Min Act: -0.1700
Data Index: 714042 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.0689. Min Act: -0.1700
Data Index: 3265551 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.0376. Min Act: -0.1700
Data Index: 6577716 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.0376. Min Act: -0.1700
Data Index: 1757574 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4439. Min Range: -6.4439
Max Act: 6.0064. Min Act: -0.1700
Data Index: 7483177 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.9439. Min Act: -0.1700
Data Index: 7497427 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.8814. Min Act: -0.1700
Data Index: 4878266 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.8501. Min Act: -0.1700
Data Index: 832412 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7164945 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.7564. Min Act: -0.1700
Data Index: 8485657 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.7564. Min Act: -0.1700
Data Index: 870936 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.7564. Min Act: -0.1700
Data Index: 2296211 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6939. Min Act: -0.1700
Data Index: 341197 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7720337 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6626. Min Act: -0.1700
Data Index: 579448 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6626. Min Act: -0.1700
Data Index: 2314046 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7182910 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4439. Min Range: -6.4439
Max Act: 5.6314. Min Act: -0.1700
Data Index: 3451295 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19