Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5710 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.6124. Min Act: -0.1700
Data Index: 5355537 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.2374. Min Act: -0.1700
Data Index: 155261 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.2374. Min Act: -0.1700
Data Index: 530310 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.1124. Min Act: -0.1700
Data Index: 8026491 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.1124. Min Act: -0.1700
Data Index: 6056177 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.0499. Min Act: -0.1700
Data Index: 2399191 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.6124. Min Range: -16.6124
Max Act: 16.0499. Min Act: -0.1700
Data Index: 2223919 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.9249. Min Act: -0.1700
Data Index: 7871170 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7999. Min Act: -0.1700
Data Index: 8324305 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7374. Min Act: -0.1700
Data Index: 6469991 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7999. Min Act: -0.1700
Data Index: 7002639 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7999. Min Act: -0.1700
Data Index: 7868384 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7999. Min Act: -0.1700
Data Index: 5787285 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.7374. Min Act: -0.1700
Data Index: 2947815 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.6749. Min Act: -0.1700
Data Index: 1637085 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.6124. Min Act: -0.1700
Data Index: 676195 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.5499. Min Act: -0.1700
Data Index: 8468899 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.5499. Min Act: -0.1700
Data Index: 8074048 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.5499. Min Act: -0.1700
Data Index: 1350192 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.6124. Min Range: -16.6124
Max Act: 15.6124. Min Act: -0.1700
Data Index: 2182063 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19