Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3629. Min Range: -8.3629
Max Act: 8.3629. Min Act: -0.1700
Data Index: 1411257 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3629. Min Range: -8.3629
Max Act: 8.1754. Min Act: -0.1700
Data Index: 7866809 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3629. Min Range: -8.3629
Max Act: 8.1129. Min Act: -0.1700
Data Index: 3388583 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3629. Min Range: -8.3629
Max Act: 8.0504. Min Act: -0.1700
Data Index: 1715577 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3629. Min Range: -8.3629
Max Act: 8.0504. Min Act: -0.1700
Data Index: 5315517 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.9254. Min Act: -0.1700
Data Index: 3553269 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.8317. Min Act: -0.1700
Data Index: 1279268 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.8629. Min Act: -0.1700
Data Index: 8200338 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.7692. Min Act: -0.1700
Data Index: 3909528 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.7379. Min Act: -0.1700
Data Index: 4482394 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.7379. Min Act: -0.1700
Data Index: 6297140 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.6442. Min Act: -0.1700
Data Index: 6436593 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.6442. Min Act: -0.1700
Data Index: 4153225 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.6754. Min Act: -0.1700
Data Index: 4033746 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.6442. Min Act: -0.1700
Data Index: 123754 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.6129. Min Act: -0.1700
Data Index: 793677 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.5504. Min Act: -0.1700
Data Index: 4270260 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.5504. Min Act: -0.1700
Data Index: 6663244 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.5504. Min Act: -0.1700
Data Index: 307388 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3629. Min Range: -8.3629
Max Act: 7.5504. Min Act: -0.1700
Data Index: 5192360 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19