Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 1328044 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.4325. Min Act: -0.1700
Data Index: 5830096 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.4012. Min Act: -0.1700
Data Index: 2729519 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3387. Min Act: -0.1700
Data Index: 845601 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3387. Min Act: -0.1700
Data Index: 3633990 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6904969 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4657395 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3075. Min Act: -0.1700
Data Index: 4579492 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2762. Min Act: -0.1700
Data Index: 8351719 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3075. Min Act: -0.1700
Data Index: 2689333 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3075. Min Act: -0.1700
Data Index: 5398443 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2762. Min Act: -0.1700
Data Index: 2305066 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2762. Min Act: -0.1700
Data Index: 3569793 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2762. Min Act: -0.1700
Data Index: 500287 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2450. Min Act: -0.1700
Data Index: 5936723 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2137. Min Act: -0.1700
Data Index: 3609973 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 7355438 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 4917415 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 2992255 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 2860047 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19