Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 139 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.8792. Min Act: -0.1700
Data Index: 437197 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7854. Min Act: -0.1700
Data Index: 7271631 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7854. Min Act: -0.1700
Data Index: 3942371 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7854. Min Act: -0.1700
Data Index: 1672772 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7541. Min Act: -0.1700
Data Index: 4348065 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7541. Min Act: -0.1700
Data Index: 5763952 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7541. Min Act: -0.1700
Data Index: 3460789 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7854. Min Act: -0.1700
Data Index: 6406017 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7541. Min Act: -0.1700
Data Index: 359390 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7541. Min Act: -0.1700
Data Index: 2811518 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.6915. Min Act: -0.1700
Data Index: 132105 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7228. Min Act: -0.1700
Data Index: 891066 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7228. Min Act: -0.1700
Data Index: 105212 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7228. Min Act: -0.1700
Data Index: 6134658 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7228. Min Act: -0.1700
Data Index: 2839308 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.7228. Min Act: -0.1700
Data Index: 2394639 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.6915. Min Act: -0.1700
Data Index: 3190728 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.6915. Min Act: -0.1700
Data Index: 3873832 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.6915. Min Act: -0.1700
Data Index: 4121885 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8792. Min Range: -3.8792
Max Act: 3.6915. Min Act: -0.1700
Data Index: 1933800 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19