Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.7539. Min Act: -0.1700
Data Index: 8744269 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.7539. Min Act: -0.1700
Data Index: 8708452 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7964496 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3476. Min Act: -0.1700
Data Index: 7672839 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3476. Min Act: -0.1700
Data Index: 6371332 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3476. Min Act: -0.1700
Data Index: 6112313 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3164. Min Act: -0.1700
Data Index: 7887706 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3164. Min Act: -0.1700
Data Index: 4518678 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3164. Min Act: -0.1700
Data Index: 5637418 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6963343 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.2539. Min Act: -0.1700
Data Index: 8730761 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.2851. Min Act: -0.1700
Data Index: 3515796 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.2539. Min Act: -0.1700
Data Index: 3240633 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.2226. Min Act: -0.1700
Data Index: 3108610 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.1914. Min Act: -0.1700
Data Index: 1343770 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.1914. Min Act: -0.1700
Data Index: 8457274 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4018014 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.1289. Min Act: -0.1700
Data Index: 2038695 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.1289. Min Act: -0.1700
Data Index: 7593931 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7539. Min Range: -6.7539
Max Act: 6.0664. Min Act: -0.1700
Data Index: 2944262 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19