Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.9197. Min Act: -0.1700
Data Index: 4890005 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8572. Min Act: -0.1700
Data Index: 7636483 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8572. Min Act: -0.1700
Data Index: 974227 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8260. Min Act: -0.1700
Data Index: 1885834 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8260. Min Act: -0.1700
Data Index: 2966289 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8260. Min Act: -0.1700
Data Index: 4095245 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.8572. Min Act: -0.1700
Data Index: 2593866 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7635. Min Act: -0.1700
Data Index: 8452332 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2407568 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7635. Min Act: -0.1700
Data Index: 7491783 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7322. Min Act: -0.1700
Data Index: 6375565 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7322. Min Act: -0.1700
Data Index: 3409008 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7322. Min Act: -0.1700
Data Index: 8780570 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7322. Min Act: -0.1700
Data Index: 6746896 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7322. Min Act: -0.1700
Data Index: 5737045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7010. Min Act: -0.1700
Data Index: 5372870 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7010. Min Act: -0.1700
Data Index: 70404 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7010. Min Act: -0.1700
Data Index: 7534319 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.6697. Min Act: -0.1700
Data Index: 5442911 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9197. Min Range: -5.9197
Max Act: 5.7010. Min Act: -0.1700
Data Index: 3101648 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19