Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4471. Min Range: -6.4471
Max Act: 6.4471. Min Act: -0.1700
Data Index: 3732769 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.9471. Min Act: -0.1700
Data Index: 5788095 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.9159. Min Act: -0.1700
Data Index: 6928163 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8846. Min Act: -0.1700
Data Index: 4006856 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8846. Min Act: -0.1700
Data Index: 2336494 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1829035 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1829036 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8221. Min Act: -0.1700
Data Index: 6385795 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 5123592 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5020505 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8221. Min Act: -0.1700
Data Index: 5020507 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8221. Min Act: -0.1700
Data Index: 2839659 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.8221. Min Act: -0.1700
Data Index: 83855 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7861391 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 6301659 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7018254 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2078657 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7909. Min Act: -0.1700
Data Index: 4026335 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7596. Min Act: -0.1700
Data Index: 6779667 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4471. Min Range: -6.4471
Max Act: 5.7596. Min Act: -0.1700
Data Index: 5028547 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19