Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6981. Min Range: -8.6981
Max Act: 8.6981. Min Act: -0.1700
Data Index: 7094097 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6981. Min Range: -8.6981
Max Act: 8.0106. Min Act: -0.1700
Data Index: 3444507 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.7606. Min Act: -0.1700
Data Index: 8456042 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.6044. Min Act: -0.1700
Data Index: 1189394 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.5731. Min Act: -0.1700
Data Index: 7203269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.4794. Min Act: -0.1700
Data Index: 51366 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.4794. Min Act: -0.1700
Data Index: 3646367 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3856. Min Act: -0.1700
Data Index: 249643 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3856. Min Act: -0.1700
Data Index: 5004727 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3544. Min Act: -0.1700
Data Index: 7298698 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3544. Min Act: -0.1700
Data Index: 3423348 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3231. Min Act: -0.1700
Data Index: 8589673 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.3231. Min Act: -0.1700
Data Index: 4897585 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.2606. Min Act: -0.1700
Data Index: 4820577 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.1981. Min Act: -0.1700
Data Index: 4243276 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.1669. Min Act: -0.1700
Data Index: 5619683 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.1981. Min Act: -0.1700
Data Index: 2402849 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.2294. Min Act: -0.1700
Data Index: 922538 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.1981. Min Act: -0.1700
Data Index: 7712677 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6981. Min Range: -8.6981
Max Act: 7.1669. Min Act: -0.1700
Data Index: 4207402 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19