Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.6322. Min Act: -0.1700
Data Index: 6203878 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.6009. Min Act: -0.1700
Data Index: 7918529 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.6009. Min Act: -0.1700
Data Index: 2218844 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.5697. Min Act: -0.1700
Data Index: 586663 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.5384. Min Act: -0.1700
Data Index: 180357 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.5072. Min Act: -0.1700
Data Index: 7385844 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2218840 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2361325 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4759. Min Act: -0.1700
Data Index: 1137318 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4759. Min Act: -0.1700
Data Index: 4062580 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2218850 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4447. Min Act: -0.1700
Data Index: 2172710 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4447. Min Act: -0.1700
Data Index: 2218837 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 722240 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 2932173 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 8815689 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 1612828 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 5042599 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 4062575 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6322. Min Range: -5.6322
Max Act: 5.4134. Min Act: -0.1700
Data Index: 7434935 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19