Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1067. Min Range: -7.1067
Max Act: 7.1067. Min Act: -0.1700
Data Index: 7120398 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.8255. Min Act: -0.1700
Data Index: 2648335 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.4192. Min Act: -0.1700
Data Index: 5316435 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.3255. Min Act: -0.1700
Data Index: 3477029 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.3255. Min Act: -0.1700
Data Index: 7706697 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 3122982 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.3255. Min Act: -0.1700
Data Index: 7556367 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.2630. Min Act: -0.1700
Data Index: 1387190 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.2317. Min Act: -0.1700
Data Index: 6037133 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.2005. Min Act: -0.1700
Data Index: 8349222 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1692. Min Act: -0.1700
Data Index: 5477066 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1692. Min Act: -0.1700
Data Index: 1239536 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1380. Min Act: -0.1700
Data Index: 8757419 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1067. Min Act: -0.1700
Data Index: 943916 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1380. Min Act: -0.1700
Data Index: 7095399 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1380. Min Act: -0.1700
Data Index: 5918502 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.1067. Min Act: -0.1700
Data Index: 5501040 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.0755. Min Act: -0.1700
Data Index: 4910363 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.0442. Min Act: -0.1700
Data Index: 1233901 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1067. Min Range: -7.1067
Max Act: 6.0755. Min Act: -0.1700
Data Index: 6391778 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19