Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.3578. Min Act: -0.1700
Data Index: 7024228 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.2165. Min Act: -0.1700
Data Index: 2817807 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.2165. Min Act: -0.1700
Data Index: 7877051 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1693. Min Act: -0.1700
Data Index: 1548277 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1535. Min Act: -0.1700
Data Index: 8697835 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1535. Min Act: -0.1700
Data Index: 5024647 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1535. Min Act: -0.1700
Data Index: 691803 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1378. Min Act: -0.1700
Data Index: 2554505 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1378. Min Act: -0.1700
Data Index: 3544704 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1063. Min Act: -0.1700
Data Index: 351351 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0905. Min Act: -0.1700
Data Index: 1922080 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.1063. Min Act: -0.1700
Data Index: 2432475 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0590. Min Act: -0.1700
Data Index: 5955101 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0590. Min Act: -0.1700
Data Index: 5488305 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0748. Min Act: -0.1700
Data Index: 907033 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0748. Min Act: -0.1700
Data Index: 1714219 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0590. Min Act: -0.1700
Data Index: 2857699 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0590. Min Act: -0.1700
Data Index: 1607133 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0590. Min Act: -0.1700
Data Index: 7017792 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3578. Min Range: -3.3578
Max Act: 3.0274. Min Act: -0.1700
Data Index: 2695708 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19