Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1724 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.7435. Min Act: -0.1700
Data Index: 293682 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.6498. Min Act: -0.1700
Data Index: 2132159 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6828471 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.5873. Min Act: -0.1700
Data Index: 3778304 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.5560. Min Act: -0.1700
Data Index: 1826967 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4935. Min Act: -0.1700
Data Index: 1204191 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.5248. Min Act: -0.1700
Data Index: 4780756 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4935. Min Act: -0.1700
Data Index: 2317709 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4935. Min Act: -0.1700
Data Index: 6874950 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4935. Min Act: -0.1700
Data Index: 4777364 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4310. Min Act: -0.1700
Data Index: 1017049 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4310. Min Act: -0.1700
Data Index: 1671353 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.4310. Min Act: -0.1700
Data Index: 1428728 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3998. Min Act: -0.1700
Data Index: 5703828 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3373. Min Act: -0.1700
Data Index: 2048700 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3373. Min Act: -0.1700
Data Index: 204310 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1736606 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3685. Min Act: -0.1700
Data Index: 5661019 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3685. Min Act: -0.1700
Data Index: 7344895 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7435. Min Range: -6.7435
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1003010 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19