Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.5731. Min Act: -0.1700
Data Index: 6275006 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.5418. Min Act: -0.1700
Data Index: 397671 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.4793. Min Act: -0.1700
Data Index: 5766068 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.4793. Min Act: -0.1700
Data Index: 654753 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.4168. Min Act: -0.1700
Data Index: 1327961 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 20809 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 3755544 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 5923376 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3856. Min Act: -0.1700
Data Index: 4856390 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 1399135 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 1680298 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 8636092 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3231. Min Act: -0.1700
Data Index: 446104 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2918. Min Act: -0.1700
Data Index: 6494714 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2606. Min Act: -0.1700
Data Index: 1695617 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2606. Min Act: -0.1700
Data Index: 4243344 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.3231. Min Act: -0.1700
Data Index: 5398006 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2606. Min Act: -0.1700
Data Index: 1525593 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2293. Min Act: -0.1700
Data Index: 475289 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5731. Min Range: -6.5731
Max Act: 6.2293. Min Act: -0.1700
Data Index: 6301408 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19