Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.8181. Min Act: -0.1700
Data Index: 4140141 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.7868. Min Act: -0.1700
Data Index: 2775399 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.7243. Min Act: -0.1700
Data Index: 6307680 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.7243. Min Act: -0.1700
Data Index: 3998124 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 7579739 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 5634048 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 4929922 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 1768938 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 1403483 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6618. Min Act: -0.1700
Data Index: 2838364 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6306. Min Act: -0.1700
Data Index: 71874 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6306. Min Act: -0.1700
Data Index: 4818912 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6306. Min Act: -0.1700
Data Index: 1044606 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6306. Min Act: -0.1700
Data Index: 5727228 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.6306. Min Act: -0.1700
Data Index: 1389610 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.5993. Min Act: -0.1700
Data Index: 4487401 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.5681. Min Act: -0.1700
Data Index: 6015969 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.5993. Min Act: -0.1700
Data Index: 2967702 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.5993. Min Act: -0.1700
Data Index: 904443 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8181. Min Range: -4.8181
Max Act: 4.5993. Min Act: -0.1700
Data Index: 6681334 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19