Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1402. Min Range: -8.1402
Max Act: 8.1402. Min Act: -0.1700
Data Index: 2692623 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.9527. Min Act: -0.1700
Data Index: 4284109 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.9527. Min Act: -0.1700
Data Index: 2267060 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.9527. Min Act: -0.1700
Data Index: 2559623 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.8902. Min Act: -0.1700
Data Index: 1245786 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.8902. Min Act: -0.1700
Data Index: 3161214 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.8277. Min Act: -0.1700
Data Index: 1239603 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.8277. Min Act: -0.1700
Data Index: 8284617 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.7339. Min Act: -0.1700
Data Index: 8531688 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.7339. Min Act: -0.1700
Data Index: 5564712 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.7339. Min Act: -0.1700
Data Index: 4633321 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5777. Min Act: -0.1700
Data Index: 7562602 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5777. Min Act: -0.1700
Data Index: 4713570 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5464. Min Act: -0.1700
Data Index: 4736643 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5464. Min Act: -0.1700
Data Index: 568347 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5152. Min Act: -0.1700
Data Index: 1089790 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5464. Min Act: -0.1700
Data Index: 807137 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5464. Min Act: -0.1700
Data Index: 8079768 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5152. Min Act: -0.1700
Data Index: 1634360 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1402. Min Range: -8.1402
Max Act: 7.5152. Min Act: -0.1700
Data Index: 5703204 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19