Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2394. Min Act: -0.1700
Data Index: 2024538 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2081. Min Act: -0.1700
Data Index: 3441630 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2394. Min Act: -0.1700
Data Index: 3274535 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2394. Min Act: -0.1700
Data Index: 4817414 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2081. Min Act: -0.1700
Data Index: 8166153 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.2081. Min Act: -0.1700
Data Index: 3880105 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1769. Min Act: -0.1700
Data Index: 7636714 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1769. Min Act: -0.1700
Data Index: 1088374 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1456. Min Act: -0.1700
Data Index: 7622591 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1769. Min Act: -0.1700
Data Index: 4906051 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1456. Min Act: -0.1700
Data Index: 1137434 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.0831. Min Act: -0.1700
Data Index: 8705105 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.0831. Min Act: -0.1700
Data Index: 5424960 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1144. Min Act: -0.1700
Data Index: 5585724 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1144. Min Act: -0.1700
Data Index: 5875966 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.0831. Min Act: -0.1700
Data Index: 1137433 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1144. Min Act: -0.1700
Data Index: 6738529 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.0831. Min Act: -0.1700
Data Index: 5476965 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.1144. Min Act: -0.1700
Data Index: 6406583 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2394. Min Range: -4.2394
Max Act: 4.0831. Min Act: -0.1700
Data Index: 3612628 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19