Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1395. Min Range: -8.1395
Max Act: 8.1395. Min Act: -0.1700
Data Index: 2698507 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1395. Min Range: -8.1395
Max Act: 8.0770. Min Act: -0.1700
Data Index: 489937 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1395. Min Range: -8.1395
Max Act: 8.0145. Min Act: -0.1700
Data Index: 91653 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.9520. Min Act: -0.1700
Data Index: 8075206 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.9520. Min Act: -0.1700
Data Index: 5640290 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.8270. Min Act: -0.1700
Data Index: 1098637 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.8895. Min Act: -0.1700
Data Index: 389132 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.8895. Min Act: -0.1700
Data Index: 1593372 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.8270. Min Act: -0.1700
Data Index: 7994334 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.8270. Min Act: -0.1700
Data Index: 180965 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7645. Min Act: -0.1700
Data Index: 914919 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7645. Min Act: -0.1700
Data Index: 6632383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 1333330 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 7212241 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 7204806 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 728409 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 2006858 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.7020. Min Act: -0.1700
Data Index: 8512128 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.6395. Min Act: -0.1700
Data Index: 3560563 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1395. Min Range: -8.1395
Max Act: 7.6395. Min Act: -0.1700
Data Index: 4568495 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19