Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 6437856 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.6141. Min Act: -0.1700
Data Index: 3624892 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.5516. Min Act: -0.1700
Data Index: 1016938 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.5204. Min Act: -0.1700
Data Index: 3446566 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.4266. Min Act: -0.1700
Data Index: 8771946 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5692853 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.4266. Min Act: -0.1700
Data Index: 2162702 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.3954. Min Act: -0.1700
Data Index: 7472994 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.4266. Min Act: -0.1700
Data Index: 7582678 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.3641. Min Act: -0.1700
Data Index: 8146816 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.3016. Min Act: -0.1700
Data Index: 1592862 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2704. Min Act: -0.1700
Data Index: 8510982 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2704. Min Act: -0.1700
Data Index: 4140247 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2704. Min Act: -0.1700
Data Index: 7439279 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2704. Min Act: -0.1700
Data Index: 6168444 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2704. Min Act: -0.1700
Data Index: 476505 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2391. Min Act: -0.1700
Data Index: 3550904 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2079. Min Act: -0.1700
Data Index: 4760376 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.2391. Min Act: -0.1700
Data Index: 4243640 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8329. Min Range: -6.8329
Max Act: 6.1766. Min Act: -0.1700
Data Index: 5987880 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19