Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.4335. Min Act: -0.1700
Data Index: 6776574 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.4021. Min Act: -0.1700
Data Index: 7159966 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3708. Min Act: -0.1700
Data Index: 4845564 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3080. Min Act: -0.1700
Data Index: 4563720 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3080. Min Act: -0.1700
Data Index: 2022815 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 5111074 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1823. Min Act: -0.1700
Data Index: 873001 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1980. Min Act: -0.1700
Data Index: 8070227 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1508. Min Act: -0.1700
Data Index: 2347200 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1823. Min Act: -0.1700
Data Index: 2022810 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1666. Min Act: -0.1700
Data Index: 2162133 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1508. Min Act: -0.1700
Data Index: 1712531 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1351. Min Act: -0.1700
Data Index: 2427313 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1193. Min Act: -0.1700
Data Index: 1217667 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1193. Min Act: -0.1700
Data Index: 3994075 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1351. Min Act: -0.1700
Data Index: 6392560 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1351. Min Act: -0.1700
Data Index: 7228574 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1508. Min Act: -0.1700
Data Index: 3797195 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.0878. Min Act: -0.1700
Data Index: 2022820 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1193. Min Act: -0.1700
Data Index: 2262045 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19