Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.6316. Min Act: -0.1700
Data Index: 2773954 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.6155. Min Act: -0.1700
Data Index: 2608699 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5833. Min Act: -0.1700
Data Index: 204090 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5994. Min Act: -0.1700
Data Index: 7964762 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5833. Min Act: -0.1700
Data Index: 172527 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5511. Min Act: -0.1700
Data Index: 1839145 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5349. Min Act: -0.1700
Data Index: 2399680 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5187. Min Act: -0.1700
Data Index: 7186918 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4701. Min Act: -0.1700
Data Index: 1688754 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4539. Min Act: -0.1700
Data Index: 4476871 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4701. Min Act: -0.1700
Data Index: 3328013 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4539. Min Act: -0.1700
Data Index: 1618348 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4376. Min Act: -0.1700
Data Index: 590996 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4376. Min Act: -0.1700
Data Index: 3199393 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4376. Min Act: -0.1700
Data Index: 5748493 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4050. Min Act: -0.1700
Data Index: 6989452 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4213. Min Act: -0.1700
Data Index: 5033033 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4213. Min Act: -0.1700
Data Index: 20583 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4213. Min Act: -0.1700
Data Index: 741028 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4213. Min Act: -0.1700
Data Index: 308405 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19