Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.5118. Min Act: -0.1700
Data Index: 7060424 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.1993. Min Act: -0.1700
Data Index: 5064166 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.1993. Min Act: -0.1700
Data Index: 2620605 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.1993. Min Act: -0.1700
Data Index: 4485579 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.0118. Min Act: -0.1700
Data Index: 1891076 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5118. Min Range: -8.5118
Max Act: 8.0118. Min Act: -0.1700
Data Index: 5525100 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 1952369 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 6088254 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 8301207 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 6225829 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 1675537 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 6443802 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.9493. Min Act: -0.1700
Data Index: 4908153 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.8868. Min Act: -0.1700
Data Index: 8434366 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.8868. Min Act: -0.1700
Data Index: 8006214 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.8243. Min Act: -0.1700
Data Index: 4541041 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.7305. Min Act: -0.1700
Data Index: 7888531 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.7305. Min Act: -0.1700
Data Index: 6662740 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.7305. Min Act: -0.1700
Data Index: 1386917 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5118. Min Range: -8.5118
Max Act: 7.6993. Min Act: -0.1700
Data Index: 1497686 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19