Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.3514. Min Act: -0.1700
Data Index: 7765887 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.3514. Min Act: -0.1700
Data Index: 4576484 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.2536. Min Act: -0.1700
Data Index: 5492793 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.2291. Min Act: -0.1700
Data Index: 6437417 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.2231. Min Act: -0.1700
Data Index: 4776521 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.2231. Min Act: -0.1700
Data Index: 4576483 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.2112. Min Act: -0.1700
Data Index: 5044568 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1879. Min Act: -0.1700
Data Index: 4776507 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1821. Min Act: -0.1700
Data Index: 4475079 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1597. Min Act: -0.1700
Data Index: 5024790 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1542. Min Act: -0.1697
Data Index: 2910275 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1488. Min Act: -0.1700
Data Index: 4029466 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1488. Min Act: -0.1700
Data Index: 3055073 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1488. Min Act: -0.1700
Data Index: 3401959 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1380. Min Act: -0.1700
Data Index: 2910273 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1222. Min Act: -0.1700
Data Index: 5262566 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1222. Min Act: -0.1700
Data Index: 7765885 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1222. Min Act: -0.1700
Data Index: 7068424 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1222. Min Act: -0.1696
Data Index: 8480288 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3514. Min Range: -0.3514
Max Act: 0.1119. Min Act: -0.1700
Data Index: 472871 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19