Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1426 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2394. Min Act: -0.1700
Data Index: 6553274 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 3359183 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1457. Min Act: -0.1700
Data Index: 2565145 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1144. Min Act: -0.1700
Data Index: 100102 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.0207. Min Act: -0.1700
Data Index: 1083015 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.9894. Min Act: -0.1700
Data Index: 7038885 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.9894. Min Act: -0.1700
Data Index: 2748419 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.9894. Min Act: -0.1700
Data Index: 4051610 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.9269. Min Act: -0.1700
Data Index: 4256696 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.9269. Min Act: -0.1700
Data Index: 3014508 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8957. Min Act: -0.1700
Data Index: 864205 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8957. Min Act: -0.1700
Data Index: 5871700 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8957. Min Act: -0.1700
Data Index: 7746869 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8644. Min Act: -0.1700
Data Index: 4671210 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8644. Min Act: -0.1700
Data Index: 4931187 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8332. Min Act: -0.1700
Data Index: 1251385 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8332. Min Act: -0.1700
Data Index: 5291093 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8332. Min Act: -0.1700
Data Index: 7712460 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8332. Min Act: -0.1700
Data Index: 7626869 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2394. Min Range: -6.2394
Max Act: 5.8019. Min Act: -0.1700
Data Index: 4452918 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19