Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9928. Min Act: -0.1700
Data Index: 8549135 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9615. Min Act: -0.1700
Data Index: 4571742 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9615. Min Act: -0.1700
Data Index: 4610851 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.8365. Min Act: -0.1700
Data Index: 3258831 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.8365. Min Act: -0.1700
Data Index: 199008 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7740. Min Act: -0.1700
Data Index: 4422221 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 2936183 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6803. Min Act: -0.1700
Data Index: 5445689 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6490. Min Act: -0.1700
Data Index: 8527306 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6803. Min Act: -0.1700
Data Index: 5275363 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6490. Min Act: -0.1700
Data Index: 1627247 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6178. Min Act: -0.1700
Data Index: 852221 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6490. Min Act: -0.1700
Data Index: 2653368 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5865. Min Act: -0.1700
Data Index: 7615152 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5865. Min Act: -0.1700
Data Index: 3136141 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5865. Min Act: -0.1700
Data Index: 750113 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5865. Min Act: -0.1700
Data Index: 1405916 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1797778 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5240. Min Act: -0.1700
Data Index: 1804120 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.4928. Min Act: -0.1700
Data Index: 1595704 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19