Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.8671. Min Act: -0.1700
Data Index: 6025424 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.5546. Min Act: -0.1700
Data Index: 6352368 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.3671. Min Act: -0.1700
Data Index: 982672 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.3671. Min Act: -0.1700
Data Index: 8344036 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.3359. Min Act: -0.1700
Data Index: 5088049 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.2734. Min Act: -0.1700
Data Index: 2731783 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.3046. Min Act: -0.1700
Data Index: 8415068 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.2421. Min Act: -0.1700
Data Index: 278229 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.2734. Min Act: -0.1700
Data Index: 6489445 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.2109. Min Act: -0.1700
Data Index: 8767317 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.2421. Min Act: -0.1700
Data Index: 8637873 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.1796. Min Act: -0.1700
Data Index: 8064985 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.1171. Min Act: -0.1700
Data Index: 5436576 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.1171. Min Act: -0.1700
Data Index: 6777841 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0859. Min Act: -0.1700
Data Index: 5142531 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0859. Min Act: -0.1700
Data Index: 2689089 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0859. Min Act: -0.1700
Data Index: 1728264 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0546. Min Act: -0.1700
Data Index: 7399039 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0859. Min Act: -0.1700
Data Index: 6352367 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8671. Min Range: -7.8671
Max Act: 7.0234. Min Act: -0.1700
Data Index: 2145491 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19