Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.4164. Min Act: -0.1700
Data Index: 1673553 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.2289. Min Act: -0.1700
Data Index: 6430435 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1664. Min Act: -0.1700
Data Index: 2290607 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1039. Min Act: -0.1700
Data Index: 1858630 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1039. Min Act: -0.1700
Data Index: 5093493 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0414. Min Act: -0.1700
Data Index: 5602997 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0102. Min Act: -0.1700
Data Index: 202350 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.9789. Min Act: -0.1700
Data Index: 4134731 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.9164. Min Act: -0.1700
Data Index: 7235266 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.8539. Min Act: -0.1700
Data Index: 5285535 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.8539. Min Act: -0.1700
Data Index: 2711961 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.8539. Min Act: -0.1700
Data Index: 4278656 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 2958991 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 5760825 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 7762892 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4883190 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4489085 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 5591134 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7221954 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4164. Min Range: -6.4164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 5840870 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19