Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 3865370 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 3994082 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 6044354 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 5171477 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 8738589 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4280. Min Act: -0.1700
Data Index: 6444865 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.4280. Min Act: -0.1700
Data Index: 1907436 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3967. Min Act: -0.1700
Data Index: 7318670 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3967. Min Act: -0.1700
Data Index: 4417745 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 2765179 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 447196 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 2610238 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 3561442 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 3179767 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 7996027 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3342. Min Act: -0.1700
Data Index: 4845629 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3342. Min Act: -0.1700
Data Index: 6590628 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3342. Min Act: -0.1700
Data Index: 6762681 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3655. Min Act: -0.1700
Data Index: 6775533 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4592. Min Range: -5.4592
Max Act: 5.3342. Min Act: -0.1700
Data Index: 2357124 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19