Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0789. Min Range: -7.0789
Max Act: 7.0789. Min Act: -0.1700
Data Index: 2172459 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.9852. Min Act: -0.1700
Data Index: 1268263 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.9539. Min Act: -0.1700
Data Index: 3916748 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.8914. Min Act: -0.1700
Data Index: 7026589 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.9227. Min Act: -0.1700
Data Index: 7614674 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.8914. Min Act: -0.1700
Data Index: 921179 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.8289. Min Act: -0.1700
Data Index: 4781949 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7977. Min Act: -0.1700
Data Index: 8474331 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7977. Min Act: -0.1700
Data Index: 5688537 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7664. Min Act: -0.1700
Data Index: 2192226 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7352. Min Act: -0.1700
Data Index: 5695069 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7352. Min Act: -0.1700
Data Index: 8439899 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7352. Min Act: -0.1700
Data Index: 4835213 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 7950540 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 1804255 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 7278460 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 1258730 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 1395937 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 2715735 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0789. Min Range: -7.0789
Max Act: 6.7039. Min Act: -0.1700
Data Index: 2984499 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19