Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.9545. Min Act: -0.1700
Data Index: 2150523 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.8607. Min Act: -0.1700
Data Index: 62828 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.8295. Min Act: -0.1700
Data Index: 5177817 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.7357. Min Act: -0.1700
Data Index: 1039161 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.7357. Min Act: -0.1700
Data Index: 913015 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.7045. Min Act: -0.1700
Data Index: 8403776 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.7045. Min Act: -0.1700
Data Index: 4804845 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.6420. Min Act: -0.1700
Data Index: 4576515 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.6420. Min Act: -0.1700
Data Index: 281592 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.5482. Min Act: -0.1700
Data Index: 8818983 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.5170. Min Act: -0.1700
Data Index: 8166328 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4857. Min Act: -0.1700
Data Index: 5773118 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4857. Min Act: -0.1700
Data Index: 1085207 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4545. Min Act: -0.1700
Data Index: 5325769 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3794062 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4545. Min Act: -0.1700
Data Index: 251738 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4545. Min Act: -0.1700
Data Index: 1384087 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4232. Min Act: -0.1700
Data Index: 2493898 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4232. Min Act: -0.1700
Data Index: 6982726 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9545. Min Range: -6.9545
Max Act: 6.4232. Min Act: -0.1700
Data Index: 5246471 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19