Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6160088 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.5471. Min Act: -0.1700
Data Index: 8712816 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.5471. Min Act: -0.1700
Data Index: 1483553 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.5471. Min Act: -0.1700
Data Index: 4150179 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.5784. Min Act: -0.1700
Data Index: 1808269 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.5159. Min Act: -0.1700
Data Index: 815826 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4846. Min Act: -0.1700
Data Index: 6762586 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4221. Min Act: -0.1700
Data Index: 5527925 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4221. Min Act: -0.1700
Data Index: 4061910 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4221. Min Act: -0.1700
Data Index: 6234909 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4221. Min Act: -0.1700
Data Index: 7536960 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.4221. Min Act: -0.1700
Data Index: 43152 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3909. Min Act: -0.1700
Data Index: 5588985 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3909. Min Act: -0.1700
Data Index: 6415570 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3596. Min Act: -0.1700
Data Index: 2329598 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3596. Min Act: -0.1700
Data Index: 3361513 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3909. Min Act: -0.1700
Data Index: 7911899 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3284. Min Act: -0.1700
Data Index: 8361390 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3284. Min Act: -0.1700
Data Index: 8294849 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7971. Min Range: -5.7971
Max Act: 5.3284. Min Act: -0.1700
Data Index: 8629028 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19