Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1594 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.5158. Min Act: -0.1700
Data Index: 7134661 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1268931 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.4220. Min Act: -0.1700
Data Index: 3752900 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.4220. Min Act: -0.1700
Data Index: 5900413 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.1720. Min Act: -0.1700
Data Index: 7654417 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.1408. Min Act: -0.1700
Data Index: 1132748 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.1408. Min Act: -0.1700
Data Index: 4096281 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.1408. Min Act: -0.1700
Data Index: 2968297 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.1408. Min Act: -0.1700
Data Index: 783305 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0783. Min Act: -0.1700
Data Index: 6726306 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0470. Min Act: -0.1700
Data Index: 8179159 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0470. Min Act: -0.1700
Data Index: 4297718 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0470. Min Act: -0.1700
Data Index: 1187373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0158. Min Act: -0.1700
Data Index: 2608340 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5158. Min Range: -6.5158
Max Act: 5.9845. Min Act: -0.1700
Data Index: 5648859 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5158. Min Range: -6.5158
Max Act: 5.9845. Min Act: -0.1700
Data Index: 200296 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5158. Min Range: -6.5158
Max Act: 6.0158. Min Act: -0.1700
Data Index: 551065 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5158. Min Range: -6.5158
Max Act: 5.9220. Min Act: -0.1700
Data Index: 8668262 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5158. Min Range: -6.5158
Max Act: 5.8908. Min Act: -0.1700
Data Index: 5893526 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5158. Min Range: -6.5158
Max Act: 5.8908. Min Act: -0.1700
Data Index: 1532442 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19