Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0579. Min Range: -10.0579
Max Act: 10.0579. Min Act: -0.1700
Data Index: 426986 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.8079. Min Act: -0.1700
Data Index: 3881191 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.6204. Min Act: -0.1700
Data Index: 5787708 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.4954. Min Act: -0.1700
Data Index: 5100904 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.4329. Min Act: -0.1700
Data Index: 7037253 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.3704. Min Act: -0.1700
Data Index: 7821460 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.4329. Min Act: -0.1700
Data Index: 5896109 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.3704. Min Act: -0.1700
Data Index: 4976430 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.2454. Min Act: -0.1700
Data Index: 2605222 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.1829. Min Act: -0.1700
Data Index: 8714606 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.1204. Min Act: -0.1700
Data Index: 4103690 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0579. Min Range: -10.0579
Max Act: 9.0579. Min Act: -0.1700
Data Index: 6366831 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 5445808 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 7038332 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 8342944 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 8385533 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 1955306 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9329. Min Act: -0.1700
Data Index: 5334988 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 8535763 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0579. Min Range: -10.0579
Max Act: 8.9954. Min Act: -0.1700
Data Index: 5697048 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19