Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.7034. Min Act: -0.1700
Data Index: 3605307 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 1527127 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.5159. Min Act: -0.1700
Data Index: 1010886 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.5159. Min Act: -0.1700
Data Index: 889830 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.5159. Min Act: -0.1700
Data Index: 4958428 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.4534. Min Act: -0.1700
Data Index: 6207943 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 6313298 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.4534. Min Act: -0.1700
Data Index: 198553 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.4534. Min Act: -0.1700
Data Index: 4599564 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.3909. Min Act: -0.1700
Data Index: 6313308 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.3284. Min Act: -0.1700
Data Index: 8560259 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.4534. Min Act: -0.1700
Data Index: 2296704 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.3284. Min Act: -0.1700
Data Index: 1527119 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.3284. Min Act: -0.1700
Data Index: 7385249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.1409. Min Act: -0.1700
Data Index: 2508670 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.2034. Min Act: -0.1700
Data Index: 3605296 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.1409. Min Act: -0.1700
Data Index: 2264933 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.1409. Min Act: -0.1700
Data Index: 4214709 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.0784. Min Act: -0.1700
Data Index: 1030449 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7034. Min Range: -9.7034
Max Act: 9.0784. Min Act: -0.1700
Data Index: 4960327 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19