Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 4582408 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 187232 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8984. Min Act: -0.1700
Data Index: 6136457 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2427435 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 6845551 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8984. Min Act: -0.1700
Data Index: 7650903 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9296. Min Act: -0.1700
Data Index: 1307637 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9296. Min Act: -0.1700
Data Index: 5474282 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 1638278 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9296. Min Act: -0.1700
Data Index: 6255183 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 6356739 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 6187668 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8984. Min Act: -0.1700
Data Index: 8290954 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8984. Min Act: -0.1700
Data Index: 8152392 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 3078347 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 572028 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 6216319 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 614665 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9296. Min Act: -0.1700
Data Index: 3925757 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 2091104 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19