Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6326 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3454. Min Range: -10.3454
Max Act: 10.3454. Min Act: -0.1700
Data Index: 2040914 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.6579. Min Act: -0.1700
Data Index: 6576245 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.5954. Min Act: -0.1700
Data Index: 3058738 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.5329. Min Act: -0.1700
Data Index: 4795571 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.5329. Min Act: -0.1700
Data Index: 4400518 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 3856336 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 916195 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4704. Min Act: -0.1700
Data Index: 4795573 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4704. Min Act: -0.1700
Data Index: 8411364 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 5932473 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 7651448 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4704. Min Act: -0.1700
Data Index: 6419380 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 4054567 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.3454. Min Act: -0.1700
Data Index: 8491266 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.4079. Min Act: -0.1700
Data Index: 457091 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.3454. Min Act: -0.1700
Data Index: 2418248 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.2829. Min Act: -0.1700
Data Index: 2797390 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.3454. Min Act: -0.1700
Data Index: 5197836 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.2829. Min Act: -0.1700
Data Index: 1175432 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3454. Min Range: -10.3454
Max Act: 9.2829. Min Act: -0.1700
Data Index: 8113965 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19