Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.2298. Min Act: -0.1700
Data Index: 1326866 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1985. Min Act: -0.1700
Data Index: 7889936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1673. Min Act: -0.1700
Data Index: 5578997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1673. Min Act: -0.1700
Data Index: 4712635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1673. Min Act: -0.1699
Data Index: 4392180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1673. Min Act: -0.1700
Data Index: 1584385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1360. Min Act: -0.1698
Data Index: 5957737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1360. Min Act: -0.1700
Data Index: 1562333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1360. Min Act: -0.1700
Data Index: 1137740 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1360. Min Act: -0.1700
Data Index: 4867522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 7970079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 4648376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 7237577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 6839140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 8033349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 8813978 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 615276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.1048. Min Act: -0.1700
Data Index: 3836731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.0735. Min Act: -0.1691
Data Index: 5652246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2298. Min Range: -5.2298
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3224756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19