Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6554. Min Range: -10.6554
Max Act: 10.6554. Min Act: -0.1700
Data Index: 8566620 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6554. Min Range: -10.6554
Max Act: 10.2804. Min Act: -0.1700
Data Index: 7933945 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6554. Min Range: -10.6554
Max Act: 10.1554. Min Act: -0.1700
Data Index: 4610914 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6554. Min Range: -10.6554
Max Act: 10.0929. Min Act: -0.1700
Data Index: 6160030 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6554. Min Range: -10.6554
Max Act: 10.0304. Min Act: -0.1700
Data Index: 7148299 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.9679. Min Act: -0.1700
Data Index: 4747133 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.9679. Min Act: -0.1700
Data Index: 8046362 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.9679. Min Act: -0.1700
Data Index: 1527663 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7804. Min Act: -0.1700
Data Index: 644370 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7804. Min Act: -0.1700
Data Index: 8404129 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7804. Min Act: -0.1700
Data Index: 8211701 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7179. Min Act: -0.1700
Data Index: 3390422 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7179. Min Act: -0.1700
Data Index: 4544947 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7179. Min Act: -0.1700
Data Index: 252750 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7179. Min Act: -0.1700
Data Index: 6764614 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.7179. Min Act: -0.1700
Data Index: 2437820 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.6554. Min Act: -0.1700
Data Index: 6901291 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.6554. Min Act: -0.1700
Data Index: 5999039 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.6554. Min Act: -0.1700
Data Index: 6542687 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6554. Min Range: -10.6554
Max Act: 9.6554. Min Act: -0.1700
Data Index: 7148306 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19