Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0796. Min Range: -10.0796
Max Act: 10.0796. Min Act: -0.1700
Data Index: 6702991 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0796. Min Range: -10.0796
Max Act: 10.0796. Min Act: -0.1700
Data Index: 3322167 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0796. Min Range: -10.0796
Max Act: 10.0796. Min Act: -0.1700
Data Index: 582145 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.9546. Min Act: -0.1700
Data Index: 4353431 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.3296. Min Act: -0.1700
Data Index: 41494 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.2671. Min Act: -0.1700
Data Index: 8655738 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.2046. Min Act: -0.1700
Data Index: 45162 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.1421. Min Act: -0.1700
Data Index: 711602 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0796. Min Act: -0.1700
Data Index: 4279191 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.1421. Min Act: -0.1700
Data Index: 5954383 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0796. Min Act: -0.1700
Data Index: 5256417 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0171. Min Act: -0.1700
Data Index: 4246911 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0171. Min Act: -0.1700
Data Index: 7547542 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0171. Min Act: -0.1700
Data Index: 8655749 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0171. Min Act: -0.1700
Data Index: 2535780 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0796. Min Range: -10.0796
Max Act: 9.0171. Min Act: -0.1700
Data Index: 4199401 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0796. Min Range: -10.0796
Max Act: 8.9546. Min Act: -0.1700
Data Index: 7727458 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0796. Min Range: -10.0796
Max Act: 8.9546. Min Act: -0.1700
Data Index: 5136442 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0796. Min Range: -10.0796
Max Act: 8.9546. Min Act: -0.1700
Data Index: 8166929 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0796. Min Range: -10.0796
Max Act: 8.8296. Min Act: -0.1700
Data Index: 254129 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19