Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.8602. Min Act: -0.1700
Data Index: 1255413 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.7039. Min Act: -0.1700
Data Index: 2542061 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.7039. Min Act: -0.1700
Data Index: 8411650 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6727. Min Act: -0.1700
Data Index: 7440346 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4852. Min Act: -0.1700
Data Index: 28502 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 38004 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4227. Min Act: -0.1700
Data Index: 4548995 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4227. Min Act: -0.1700
Data Index: 3814690 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4227. Min Act: -0.1700
Data Index: 2353223 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4227. Min Act: -0.1700
Data Index: 8628838 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4227. Min Act: -0.1700
Data Index: 7205948 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3602. Min Act: -0.1700
Data Index: 1480363 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 6252698 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 3129754 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 6630335 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 2762822 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 2526615 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.2977. Min Act: -0.1700
Data Index: 768056 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3289. Min Act: -0.1700
Data Index: 5244165 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.3602. Min Act: -0.1700
Data Index: 7575952 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19