Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.9190. Min Act: -0.1700
Data Index: 3803276 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.8565. Min Act: -0.1700
Data Index: 6189400 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.8565. Min Act: -0.1700
Data Index: 8454993 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.7940. Min Act: -0.1700
Data Index: 6952283 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.7315. Min Act: -0.1700
Data Index: 6316161 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6690. Min Act: -0.1700
Data Index: 4686891 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6690. Min Act: -0.1700
Data Index: 1111397 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6690. Min Act: -0.1700
Data Index: 5436621 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6065. Min Act: -0.1700
Data Index: 8352576 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6378. Min Act: -0.1700
Data Index: 3313366 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6378. Min Act: -0.1700
Data Index: 2083665 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6065. Min Act: -0.1700
Data Index: 3415287 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.6065. Min Act: -0.1700
Data Index: 1940918 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5440. Min Act: -0.1700
Data Index: 393748 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5440. Min Act: -0.1700
Data Index: 1946683 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4143670 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4698442 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5128. Min Act: -0.1700
Data Index: 6497218 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5128. Min Act: -0.1700
Data Index: 8663847 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9190. Min Range: -4.9190
Max Act: 4.5128. Min Act: -0.1700
Data Index: 2739803 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19