Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1188 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.8414. Min Act: -0.1700
Data Index: 3623750 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.6539. Min Act: -0.1700
Data Index: 4537867 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.5289. Min Act: -0.1700
Data Index: 8229005 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.5289. Min Act: -0.1700
Data Index: 699700 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.4664. Min Act: -0.1700
Data Index: 5663572 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.4351. Min Act: -0.1700
Data Index: 5402541 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.3726. Min Act: -0.1700
Data Index: 7105893 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.3726. Min Act: -0.1700
Data Index: 2555598 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.3414. Min Act: -0.1700
Data Index: 415969 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.3414. Min Act: -0.1700
Data Index: 4536380 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.3101. Min Act: -0.1700
Data Index: 7238024 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2789. Min Act: -0.1700
Data Index: 7313456 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2476. Min Act: -0.1700
Data Index: 4144965 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2476. Min Act: -0.1700
Data Index: 8179095 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2164. Min Act: -0.1700
Data Index: 6125913 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.1851. Min Act: -0.1700
Data Index: 928541 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2164. Min Act: -0.1700
Data Index: 644460 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2476. Min Act: -0.1700
Data Index: 3526226 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.1539. Min Act: -0.1700
Data Index: 7494232 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8414. Min Range: -6.8414
Max Act: 6.2164. Min Act: -0.1700
Data Index: 8051660 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19