Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2386. Min Range: -6.2386
Max Act: 6.2386. Min Act: -0.1700
Data Index: 7705647 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2386. Min Range: -6.2386
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5696869 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2386. Min Range: -6.2386
Max Act: 6.0823. Min Act: -0.1700
Data Index: 2952485 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2386. Min Range: -6.2386
Max Act: 6.1136. Min Act: -0.1700
Data Index: 6622626 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2386. Min Range: -6.2386
Max Act: 6.0511. Min Act: -0.1700
Data Index: 198260 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.9573. Min Act: -0.1700
Data Index: 5457036 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3560503 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.9573. Min Act: -0.1700
Data Index: 77926 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.9573. Min Act: -0.1700
Data Index: 1211354 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.9261. Min Act: -0.1700
Data Index: 4500265 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8948. Min Act: -0.1700
Data Index: 6038188 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8636. Min Act: -0.1700
Data Index: 1511962 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8011. Min Act: -0.1700
Data Index: 1193822 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8323. Min Act: -0.1700
Data Index: 5849908 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8323. Min Act: -0.1700
Data Index: 2890683 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7790917 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8011. Min Act: -0.1700
Data Index: 3606921 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2938740 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.7698. Min Act: -0.1700
Data Index: 4203709 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2386. Min Range: -6.2386
Max Act: 5.8011. Min Act: -0.1700
Data Index: 387746 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19