Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.3313. Min Act: -0.1700
Data Index: 5940849 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.2375. Min Act: -0.1700
Data Index: 1625426 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.1125. Min Act: -0.1700
Data Index: 1848776 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.1438. Min Act: -0.1700
Data Index: 6081385 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.1125. Min Act: -0.1700
Data Index: 8229649 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0813. Min Act: -0.1700
Data Index: 4685704 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0500. Min Act: -0.1700
Data Index: 286370 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0500. Min Act: -0.1700
Data Index: 4377860 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5938404 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0188. Min Act: -0.1700
Data Index: 1271336 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0188. Min Act: -0.1700
Data Index: 7922310 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0188. Min Act: -0.1700
Data Index: 4164766 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3313. Min Range: -5.3313
Max Act: 5.0188. Min Act: -0.1700
Data Index: 7790538 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9563. Min Act: -0.1700
Data Index: 7483458 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9875. Min Act: -0.1700
Data Index: 8446187 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9875. Min Act: -0.1700
Data Index: 6469552 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9563. Min Act: -0.1700
Data Index: 1357348 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9875. Min Act: -0.1700
Data Index: 5045970 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9875. Min Act: -0.1700
Data Index: 6117132 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3313. Min Range: -5.3313
Max Act: 4.9563. Min Act: -0.1700
Data Index: 3380047 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19