Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.9659. Min Act: -0.1700
Data Index: 1226626 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.9346. Min Act: -0.1700
Data Index: 247864 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.8408. Min Act: -0.1700
Data Index: 1433198 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.8408. Min Act: -0.1700
Data Index: 6056893 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.8096. Min Act: -0.1700
Data Index: 5067379 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.8096. Min Act: -0.1700
Data Index: 1716745 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4805681 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.7157. Min Act: -0.1700
Data Index: 7145368 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6844. Min Act: -0.1700
Data Index: 2699151 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6844. Min Act: -0.1700
Data Index: 3767794 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6844. Min Act: -0.1700
Data Index: 510922 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 2778683 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 2474097 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 5027393 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 6315185 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 4252658 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 4004528 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6218. Min Act: -0.1700
Data Index: 542779 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6531. Min Act: -0.1700
Data Index: 2658316 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9659. Min Range: -3.9659
Max Act: 3.6218. Min Act: -0.1700
Data Index: 5483047 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19