Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1699 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2985. Min Act: -0.1700
Data Index: 8360599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2985. Min Act: -0.1700
Data Index: 7534925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2720. Min Act: -0.1700
Data Index: 5142114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2544. Min Act: -0.1700
Data Index: 2819551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2456. Min Act: -0.1700
Data Index: 2294929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2456. Min Act: -0.1700
Data Index: 1811334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2191. Min Act: -0.1700
Data Index: 8396801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2015. Min Act: -0.1700
Data Index: 1634308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2103. Min Act: -0.1700
Data Index: 3234305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2103. Min Act: -0.1700
Data Index: 1956498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1927. Min Act: -0.1700
Data Index: 3860979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2015. Min Act: -0.1700
Data Index: 2995666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2015. Min Act: -0.1700
Data Index: 2835113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.2015. Min Act: -0.1700
Data Index: 7351992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1751. Min Act: -0.1700
Data Index: 7847348 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1839. Min Act: -0.1700
Data Index: 8302789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1751. Min Act: -0.1700
Data Index: 8135084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1751. Min Act: -0.1700
Data Index: 1389748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1663. Min Act: -0.1700
Data Index: 6207032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2985. Min Range: -1.2985
Max Act: 1.1663. Min Act: -0.1700
Data Index: 4672709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19