Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.9416. Min Act: -0.1700
Data Index: 788048 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.8166. Min Act: -0.1700
Data Index: 2163348 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.7541. Min Act: -0.1700
Data Index: 3000534 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6916. Min Act: -0.1700
Data Index: 3654655 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6916. Min Act: -0.1700
Data Index: 7650559 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6916. Min Act: -0.1700
Data Index: 8399595 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6916. Min Act: -0.1700
Data Index: 3535410 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6291. Min Act: -0.1700
Data Index: 4908700 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.6291. Min Act: -0.1700
Data Index: 3141538 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5666. Min Act: -0.1700
Data Index: 6458607 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5666. Min Act: -0.1700
Data Index: 5726282 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5041. Min Act: -0.1700
Data Index: 2648182 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5041. Min Act: -0.1700
Data Index: 2201006 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5041. Min Act: -0.1700
Data Index: 4997153 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.5041. Min Act: -0.1700
Data Index: 2921268 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.3791. Min Act: -0.1700
Data Index: 3875635 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.3791. Min Act: -0.1700
Data Index: 6073286 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.3166. Min Act: -0.1700
Data Index: 4745548 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.3166. Min Act: -0.1700
Data Index: 1134933 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9416. Min Range: -9.9416
Max Act: 9.3166. Min Act: -0.1700
Data Index: 6316114 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19