Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.9302. Min Act: -0.1700
Data Index: 6909615 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.9302. Min Act: -0.1700
Data Index: 4649643 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.9302. Min Act: -0.1700
Data Index: 636184 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8990. Min Act: -0.1700
Data Index: 839915 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4624625 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8990. Min Act: -0.1700
Data Index: 8159947 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8677. Min Act: -0.1700
Data Index: 5764895 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8365. Min Act: -0.1700
Data Index: 401930 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8365. Min Act: -0.1700
Data Index: 2535562 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8365. Min Act: -0.1700
Data Index: 8079554 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8365. Min Act: -0.1700
Data Index: 2504386 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8052. Min Act: -0.1700
Data Index: 8784150 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 901925 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8052. Min Act: -0.1700
Data Index: 5028593 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.8052. Min Act: -0.1700
Data Index: 7809115 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 785650 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 3219252 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 8363539 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4168274 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9302. Min Range: -4.9302
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4513983 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19