Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1979 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5122. Min Range: -9.5122
Max Act: 9.5122. Min Act: -0.1700
Data Index: 5727767 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5122. Min Range: -9.5122
Max Act: 9.0747. Min Act: -0.1700
Data Index: 6781922 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.9497. Min Act: -0.1700
Data Index: 5482219 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.8872. Min Act: -0.1700
Data Index: 6595159 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.8872. Min Act: -0.1700
Data Index: 2766655 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.9497. Min Act: -0.1700
Data Index: 552317 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.8247. Min Act: -0.1700
Data Index: 975090 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.7622. Min Act: -0.1700
Data Index: 1631663 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6997. Min Act: -0.1700
Data Index: 5217646 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6997. Min Act: -0.1700
Data Index: 1813771 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6997. Min Act: -0.1700
Data Index: 2153619 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6372. Min Act: -0.1700
Data Index: 7635978 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.5747. Min Act: -0.1700
Data Index: 3559878 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6997. Min Act: -0.1700
Data Index: 6361350 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6997. Min Act: -0.1700
Data Index: 6983900 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6372. Min Act: -0.1700
Data Index: 7359738 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.5747. Min Act: -0.1700
Data Index: 6314403 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.5747. Min Act: -0.1700
Data Index: 13201 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.6372. Min Act: -0.1700
Data Index: 4055097 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5122. Min Range: -9.5122
Max Act: 8.5122. Min Act: -0.1700
Data Index: 1201889 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19