Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 8423768 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 5055343 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.7459. Min Act: -0.1700
Data Index: 5739769 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.4959. Min Act: -0.1700
Data Index: 5287395 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.4646. Min Act: -0.1700
Data Index: 3125680 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.4021. Min Act: -0.1700
Data Index: 3730906 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.3709. Min Act: -0.1700
Data Index: 6155407 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.3709. Min Act: -0.1700
Data Index: 446926 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.3396. Min Act: -0.1700
Data Index: 4204992 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.2771. Min Act: -0.1700
Data Index: 3487122 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.2459. Min Act: -0.1700
Data Index: 699850 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.2459. Min Act: -0.1700
Data Index: 3307787 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.2146. Min Act: -0.1700
Data Index: 2908689 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1521. Min Act: -0.1700
Data Index: 7495679 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1521. Min Act: -0.1700
Data Index: 7946376 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1521. Min Act: -0.1700
Data Index: 6793158 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1521. Min Act: -0.1700
Data Index: 7595990 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1521. Min Act: -0.1700
Data Index: 6846670 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.1209. Min Act: -0.1700
Data Index: 8386430 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9334. Min Range: -7.9334
Max Act: 7.0896. Min Act: -0.1700
Data Index: 6427002 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19