Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.7321. Min Act: -0.1700
Data Index: 412129 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.7321. Min Act: -0.1700
Data Index: 4706611 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.6383. Min Act: -0.1700
Data Index: 5894066 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.6071. Min Act: -0.1700
Data Index: 5894067 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.5133. Min Act: -0.1700
Data Index: 2096309 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4821. Min Act: -0.1700
Data Index: 5791502 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.5133. Min Act: -0.1700
Data Index: 4751959 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4508. Min Act: -0.1700
Data Index: 5791503 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4196. Min Act: -0.1700
Data Index: 3689729 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3883. Min Act: -0.1700
Data Index: 5914700 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3571. Min Act: -0.1700
Data Index: 5914701 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3258. Min Act: -0.1700
Data Index: 4903206 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2946. Min Act: -0.1700
Data Index: 1130424 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3258. Min Act: -0.1700
Data Index: 7234994 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2946. Min Act: -0.1700
Data Index: 822649 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2633. Min Act: -0.1700
Data Index: 3748446 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 6200291 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 1817757 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 7644224 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2008. Min Act: -0.1700
Data Index: 5896076 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19