Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0430. Min Range: -4.0430
Max Act: 4.0430. Min Act: -0.1700
Data Index: 8099612 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0430. Min Range: -4.0430
Max Act: 4.0273. Min Act: -0.1700
Data Index: 1219455 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.9179. Min Act: -0.1700
Data Index: 2207077 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.8241. Min Act: -0.1700
Data Index: 4650257 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.8085. Min Act: -0.1700
Data Index: 6201217 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.8085. Min Act: -0.1700
Data Index: 8522671 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6901726 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6300794 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7616. Min Act: -0.1700
Data Index: 6451569 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7303. Min Act: -0.1700
Data Index: 5274537 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7146. Min Act: -0.1700
Data Index: 7019834 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7303. Min Act: -0.1700
Data Index: 4997549 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7303. Min Act: -0.1700
Data Index: 4725907 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7146. Min Act: -0.1700
Data Index: 7301609 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7303. Min Act: -0.1700
Data Index: 92179 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7146. Min Act: -0.1700
Data Index: 906492 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7459. Min Act: -0.1700
Data Index: 414695 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.7303. Min Act: -0.1700
Data Index: 6194330 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.6833. Min Act: -0.1700
Data Index: 4822891 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0430. Min Range: -4.0430
Max Act: 3.6833. Min Act: -0.1700
Data Index: 6872234 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19