Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1353 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.7053. Min Act: -0.1700
Data Index: 1273621 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.5801. Min Act: -0.1700
Data Index: 1144510 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2980. Min Act: -0.1700
Data Index: 4865943 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.3451. Min Act: -0.1700
Data Index: 7601709 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.3294. Min Act: -0.1700
Data Index: 919145 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2980. Min Act: -0.1700
Data Index: 8211881 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2823. Min Act: -0.1700
Data Index: 7736164 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2980. Min Act: -0.1700
Data Index: 5809642 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2509. Min Act: -0.1700
Data Index: 276051 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.3294. Min Act: -0.1700
Data Index: 5856076 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2666. Min Act: -0.1700
Data Index: 5187071 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2823. Min Act: -0.1700
Data Index: 1655900 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2352. Min Act: -0.1700
Data Index: 6939367 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2666. Min Act: -0.1700
Data Index: 3331664 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2509. Min Act: -0.1700
Data Index: 7517969 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2195. Min Act: -0.1700
Data Index: 1462878 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.3294. Min Act: -0.1700
Data Index: 1928873 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2195. Min Act: -0.1700
Data Index: 4030441 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2352. Min Act: -0.1700
Data Index: 2809192 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7053. Min Range: -3.7053
Max Act: 3.2037. Min Act: -0.1700
Data Index: 825499 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19