Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.2166. Min Act: -0.1700
Data Index: 1917341 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1853. Min Act: -0.1700
Data Index: 3608918 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1540. Min Act: -0.1700
Data Index: 3851269 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1540. Min Act: -0.1700
Data Index: 7338444 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5657816 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0915. Min Act: -0.1700
Data Index: 8765948 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0915. Min Act: -0.1700
Data Index: 3961276 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0915. Min Act: -0.1700
Data Index: 7637648 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 6595631 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 4356182 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 5587358 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 4788923 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0290. Min Act: -0.1700
Data Index: 1878490 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0290. Min Act: -0.1700
Data Index: 3079186 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0290. Min Act: -0.1700
Data Index: 7593075 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0290. Min Act: -0.1700
Data Index: 2469169 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9665. Min Act: -0.1700
Data Index: 4356168 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9352. Min Act: -0.1700
Data Index: 7831035 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9665. Min Act: -0.1700
Data Index: 1736862 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9040. Min Act: -0.1700
Data Index: 101885 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19