Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.6127. Min Act: -0.1700
Data Index: 7928096 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.5814. Min Act: -0.1700
Data Index: 3194432 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.4877. Min Act: -0.1700
Data Index: 8419516 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3627. Min Act: -0.1700
Data Index: 4281079 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3627. Min Act: -0.1700
Data Index: 5398094 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3627. Min Act: -0.1700
Data Index: 7044824 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3314. Min Act: -0.1700
Data Index: 5614730 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3002. Min Act: -0.1700
Data Index: 5687379 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3314. Min Act: -0.1700
Data Index: 8431028 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3002. Min Act: -0.1700
Data Index: 1688364 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3002. Min Act: -0.1700
Data Index: 5348155 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3002. Min Act: -0.1700
Data Index: 4830778 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.3002. Min Act: -0.1700
Data Index: 7469628 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2689. Min Act: -0.1700
Data Index: 7398780 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2377. Min Act: -0.1700
Data Index: 2539164 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2689. Min Act: -0.1700
Data Index: 122897 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2377. Min Act: -0.1700
Data Index: 2343105 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2064. Min Act: -0.1700
Data Index: 5118337 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2377. Min Act: -0.1700
Data Index: 153681 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6127. Min Range: -7.6127
Max Act: 7.2689. Min Act: -0.1700
Data Index: 1031584 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19