Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 3876890 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.2836. Min Act: -0.1700
Data Index: 8774903 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.2211. Min Act: -0.1700
Data Index: 1993574 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.1898. Min Act: -0.1700
Data Index: 175664 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0648. Min Act: -0.1700
Data Index: 4313322 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0960. Min Act: -0.1700
Data Index: 7742366 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0023. Min Act: -0.1700
Data Index: 5363398 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0335. Min Act: -0.1700
Data Index: 1207815 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0023. Min Act: -0.1700
Data Index: 2986272 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0023. Min Act: -0.1700
Data Index: 3083629 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3148. Min Range: -4.3148
Max Act: 4.0023. Min Act: -0.1700
Data Index: 5935534 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9710. Min Act: -0.1700
Data Index: 5354518 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9710. Min Act: -0.1700
Data Index: 4729758 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9397. Min Act: -0.1700
Data Index: 7438732 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9397. Min Act: -0.1700
Data Index: 4833446 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9397. Min Act: -0.1700
Data Index: 2448334 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9397. Min Act: -0.1700
Data Index: 512844 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9085. Min Act: -0.1700
Data Index: 796473 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9085. Min Act: -0.1700
Data Index: 5544865 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3148. Min Range: -4.3148
Max Act: 3.9085. Min Act: -0.1700
Data Index: 232285 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19