Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.7873. Min Act: -0.1700
Data Index: 2769624 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.5373. Min Act: -0.1700
Data Index: 1763725 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.3810. Min Act: -0.1700
Data Index: 2415387 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.2873. Min Act: -0.1700
Data Index: 7242236 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.1935. Min Act: -0.1700
Data Index: 3221899 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0685. Min Act: -0.1700
Data Index: 3013973 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0373. Min Act: -0.1700
Data Index: 1006432 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0060. Min Act: -0.1700
Data Index: 2469868 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0373. Min Act: -0.1700
Data Index: 3220130 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0373. Min Act: -0.1700
Data Index: 6305062 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0998. Min Act: -0.1700
Data Index: 7296915 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0060. Min Act: -0.1700
Data Index: 2349012 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7873. Min Range: -6.7873
Max Act: 6.0373. Min Act: -0.1700
Data Index: 6302475 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9435. Min Act: -0.1700
Data Index: 6711956 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9435. Min Act: -0.1700
Data Index: 4327460 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9748. Min Act: -0.1700
Data Index: 5533355 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9123. Min Act: -0.1700
Data Index: 7686586 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9435. Min Act: -0.1700
Data Index: 3898733 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9748. Min Act: -0.1700
Data Index: 5201329 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7873. Min Range: -6.7873
Max Act: 5.9123. Min Act: -0.1700
Data Index: 7948958 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19