Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.6562. Min Act: -0.1700
Data Index: 4611263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4687. Min Range: -8.4687
Max Act: 8.4687. Min Act: -0.1695
Data Index: 568105 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4687. Min Range: -8.4687
Max Act: 8.2187. Min Act: -0.1700
Data Index: 4625765 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.9062. Min Act: -0.1700
Data Index: 1018370 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.4375. Min Act: -0.1700
Data Index: 5802535 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.3437. Min Act: -0.1700
Data Index: 1238878 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.3125. Min Act: -0.1700
Data Index: 5951208 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.3437. Min Act: -0.1700
Data Index: 902854 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.1562. Min Act: -0.1700
Data Index: 8764978 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.1250. Min Act: -0.1700
Data Index: 7873931 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.1250. Min Act: -0.1700
Data Index: 3384925 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.0937. Min Act: -0.1700
Data Index: 8460228 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.0937. Min Act: -0.1700
Data Index: 5058945 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.0312. Min Act: -0.1700
Data Index: 1432551 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4687. Min Range: -8.4687
Max Act: 6.9687. Min Act: -0.1700
Data Index: 4419802 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4687. Min Range: -8.4687
Max Act: 7.0312. Min Act: -0.1700
Data Index: 8128509 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4687. Min Range: -8.4687
Max Act: 6.9375. Min Act: -0.1700
Data Index: 6419875 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4687. Min Range: -8.4687
Max Act: 6.9687. Min Act: -0.1700
Data Index: 7262776 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4687. Min Range: -8.4687
Max Act: 6.8750. Min Act: -0.1700
Data Index: 5378006 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4687. Min Range: -8.4687
Max Act: 6.8437. Min Act: -0.1700
Data Index: 301252 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19