Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.6171. Min Act: -0.1700
Data Index: 8243531 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.3671. Min Act: -0.1700
Data Index: 222504 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.3359. Min Act: -0.1700
Data Index: 7856311 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.2734. Min Act: -0.1700
Data Index: 4108298 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.2109. Min Act: -0.1700
Data Index: 6305446 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.1796. Min Act: -0.1700
Data Index: 8139893 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.1171. Min Act: -0.1700
Data Index: 2347583 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.1796. Min Act: -0.1700
Data Index: 410007 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.1484. Min Act: -0.1700
Data Index: 7923343 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.1171. Min Act: -0.1700
Data Index: 4926275 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.0859. Min Act: -0.1700
Data Index: 3888894 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.0234. Min Act: -0.1700
Data Index: 8308665 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6171. Min Range: -7.6171
Max Act: 7.0234. Min Act: -0.1700
Data Index: 3679774 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.9609. Min Act: -0.1700
Data Index: 401541 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8984. Min Act: -0.1700
Data Index: 2626857 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8671. Min Act: -0.1700
Data Index: 1130466 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8359. Min Act: -0.1700
Data Index: 322204 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8046. Min Act: -0.1700
Data Index: 492677 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8046. Min Act: -0.1700
Data Index: 877852 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6171. Min Range: -7.6171
Max Act: 6.8359. Min Act: -0.1700
Data Index: 3073035 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19