Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4069 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3520. Min Act: -0.1700
Data Index: 8278398 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3520. Min Act: -0.1700
Data Index: 1467921 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3207. Min Act: -0.1700
Data Index: 749205 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3207. Min Act: -0.1700
Data Index: 2069171 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 4242371 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 3066188 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 3113428 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 7636000 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 7886943 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 3302514 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 250705 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 755773 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3953129 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3448565 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3266428 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 6311746 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 5011193 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 1913392 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 3543399 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 4060892 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19