Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4986 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.7002. Min Act: -0.1700
Data Index: 8397439 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.7002. Min Act: -0.1700
Data Index: 5537172 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.7002. Min Act: -0.1700
Data Index: 1896393 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.7002. Min Act: -0.1700
Data Index: 4168347 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.7002. Min Act: -0.1700
Data Index: 6963510 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6690. Min Act: -0.1700
Data Index: 776273 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 3592824 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 7443431 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 3792191 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6690. Min Act: -0.1700
Data Index: 8642525 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 6659941 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 1864153 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 6172171 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 4345987 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 4354161 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6377. Min Act: -0.1700
Data Index: 4873081 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6065. Min Act: -0.1700
Data Index: 1756005 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6065. Min Act: -0.1700
Data Index: 2336741 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6065. Min Act: -0.1700
Data Index: 4504357 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7002. Min Range: -5.7002
Max Act: 5.6065. Min Act: -0.1700
Data Index: 1087490 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19