Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2285 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4256. Min Range: -10.4256
Max Act: 10.4256. Min Act: -0.1700
Data Index: 7928153 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4256. Min Range: -10.4256
Max Act: 10.4256. Min Act: -0.1700
Data Index: 7061568 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4256. Min Range: -10.4256
Max Act: 10.2381. Min Act: -0.1700
Data Index: 4003693 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4256. Min Range: -10.4256
Max Act: 10.1756. Min Act: -0.1700
Data Index: 1541640 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.9881. Min Act: -0.1700
Data Index: 347720 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.7381. Min Act: -0.1700
Data Index: 3565670 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.7381. Min Act: -0.1700
Data Index: 289609 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.9256. Min Act: -0.1700
Data Index: 2109377 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6756. Min Act: -0.1700
Data Index: 6878378 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6131. Min Act: -0.1700
Data Index: 3742792 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6131. Min Act: -0.1700
Data Index: 4948454 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.8006. Min Act: -0.1591
Data Index: 1587787 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6756. Min Act: -0.1700
Data Index: 3564031 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6756. Min Act: -0.1700
Data Index: 371370 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.5506. Min Act: -0.1700
Data Index: 5305906 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6131. Min Act: -0.1700
Data Index: 7928796 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.5506. Min Act: -0.1700
Data Index: 3128806 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.6131. Min Act: -0.1700
Data Index: 6688111 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.5506. Min Act: -0.1700
Data Index: 6743168 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4256. Min Range: -10.4256
Max Act: 9.5506. Min Act: -0.1700
Data Index: 5155773 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19