Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.5171. Min Act: -0.1700
Data Index: 4762310 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.5171. Min Act: -0.1700
Data Index: 2938882 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.4546. Min Act: -0.1700
Data Index: 5383119 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.3921. Min Act: -0.1700
Data Index: 122973 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.4233. Min Act: -0.1700
Data Index: 5931330 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.2671. Min Act: -0.1700
Data Index: 4833536 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.2358. Min Act: -0.1700
Data Index: 4071935 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.2046. Min Act: -0.1700
Data Index: 2791428 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.2358. Min Act: -0.1700
Data Index: 8078011 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.2046. Min Act: -0.1700
Data Index: 5004677 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.1421. Min Act: -0.1700
Data Index: 6381659 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.1108. Min Act: -0.1700
Data Index: 833636 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.1421. Min Act: -0.1700
Data Index: 2666977 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.1108. Min Act: -0.1700
Data Index: 2817586 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.0483. Min Act: -0.1700
Data Index: 1544729 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.1108. Min Act: -0.1700
Data Index: 4602674 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.0796. Min Act: -0.1700
Data Index: 3772039 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.0796. Min Act: -0.1700
Data Index: 7575838 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.0483. Min Act: -0.1700
Data Index: 4211377 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5171. Min Range: -7.5171
Max Act: 7.0483. Min Act: -0.1700
Data Index: 4014066 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19