Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2174 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.5817. Min Act: -0.1700
Data Index: 7923509 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.4255. Min Act: -0.1700
Data Index: 4661961 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.3630. Min Act: -0.1700
Data Index: 7851718 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2692. Min Act: -0.1700
Data Index: 4530936 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2692. Min Act: -0.1700
Data Index: 1870990 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.3005. Min Act: -0.1700
Data Index: 2458201 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2692. Min Act: -0.1700
Data Index: 4206512 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2692. Min Act: -0.1700
Data Index: 4224296 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2380. Min Act: -0.1700
Data Index: 5134721 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2067. Min Act: -0.1700
Data Index: 8211045 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2067. Min Act: -0.1700
Data Index: 3859650 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.2067. Min Act: -0.1700
Data Index: 7335129 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1755. Min Act: -0.1700
Data Index: 5045010 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1442. Min Act: -0.1700
Data Index: 3791413 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1442. Min Act: -0.1700
Data Index: 8817808 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1130. Min Act: -0.1700
Data Index: 4383519 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1130. Min Act: -0.1700
Data Index: 3145036 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1130. Min Act: -0.1700
Data Index: 174654 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1130. Min Act: -0.1700
Data Index: 6545543 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5817. Min Range: -5.5817
Max Act: 5.1130. Min Act: -0.1700
Data Index: 5812880 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19