Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.2674. Min Act: -0.1700
Data Index: 3103998 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.2674. Min Act: -0.1700
Data Index: 1509717 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.1424. Min Act: -0.1700
Data Index: 1642025 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.1112. Min Act: -0.1700
Data Index: 1279548 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.0487. Min Act: -0.1700
Data Index: 6555766 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2674. Min Range: -6.2674
Max Act: 6.0174. Min Act: -0.1700
Data Index: 1334705 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.9862. Min Act: -0.1700
Data Index: 8329967 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.9237. Min Act: -0.1700
Data Index: 747724 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8924. Min Act: -0.1700
Data Index: 7767659 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8924. Min Act: -0.1700
Data Index: 3545997 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4355231 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8612. Min Act: -0.1700
Data Index: 2488143 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8299. Min Act: -0.1700
Data Index: 6227496 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.8299. Min Act: -0.1700
Data Index: 8700224 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7701404 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7987. Min Act: -0.1700
Data Index: 8035020 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7674. Min Act: -0.1700
Data Index: 2914077 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7674. Min Act: -0.1700
Data Index: 2010119 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7674. Min Act: -0.1700
Data Index: 867913 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2674. Min Range: -6.2674
Max Act: 5.7674. Min Act: -0.1700
Data Index: 6458542 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19