Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2209. Min Range: -6.2209
Max Act: 6.2209. Min Act: -0.1700
Data Index: 1993350 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2209. Min Range: -6.2209
Max Act: 6.1896. Min Act: -0.1700
Data Index: 4787257 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2209. Min Range: -6.2209
Max Act: 6.0334. Min Act: -0.1700
Data Index: 52624 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9709. Min Act: -0.1700
Data Index: 1301048 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9709. Min Act: -0.1700
Data Index: 8295315 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9396. Min Act: -0.1700
Data Index: 557575 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9396. Min Act: -0.1700
Data Index: 3711500 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9396. Min Act: -0.1700
Data Index: 1841750 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9084. Min Act: -0.1700
Data Index: 2526510 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8771. Min Act: -0.1700
Data Index: 76727 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8771. Min Act: -0.1700
Data Index: 168263 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.9084. Min Act: -0.1700
Data Index: 7292027 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8771. Min Act: -0.1700
Data Index: 7488714 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8146. Min Act: -0.1700
Data Index: 6277328 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8459. Min Act: -0.1700
Data Index: 8127611 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8771. Min Act: -0.1700
Data Index: 1611621 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8146. Min Act: -0.1700
Data Index: 7731011 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8146. Min Act: -0.1700
Data Index: 8566766 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8146. Min Act: -0.1700
Data Index: 51266 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2209. Min Range: -6.2209
Max Act: 5.8146. Min Act: -0.1700
Data Index: 5906408 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19