Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0943. Min Range: -3.0943
Max Act: 3.0943. Min Act: -0.1700
Data Index: 6619281 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0943. Min Range: -3.0943
Max Act: 3.0785. Min Act: -0.1700
Data Index: 4090480 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0943. Min Range: -3.0943
Max Act: 3.0469. Min Act: -0.1700
Data Index: 1070355 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0943. Min Range: -3.0943
Max Act: 3.0312. Min Act: -0.1700
Data Index: 5391468 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0943. Min Range: -3.0943
Max Act: 3.0312. Min Act: -0.1700
Data Index: 2794610 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9996. Min Act: -0.1700
Data Index: 3791309 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9679. Min Act: -0.1700
Data Index: 2032499 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9838. Min Act: -0.1700
Data Index: 7598979 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9679. Min Act: -0.1700
Data Index: 4090481 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9521. Min Act: -0.1700
Data Index: 3002925 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9521. Min Act: -0.1700
Data Index: 2859765 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9521. Min Act: -0.1700
Data Index: 2514862 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9363. Min Act: -0.1700
Data Index: 2460586 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9679. Min Act: -0.1700
Data Index: 92908 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9363. Min Act: -0.1700
Data Index: 100286 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9363. Min Act: -0.1700
Data Index: 4090482 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9204. Min Act: -0.1700
Data Index: 7930254 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9363. Min Act: -0.1700
Data Index: 7598981 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9204. Min Act: -0.1700
Data Index: 6483703 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0943. Min Range: -3.0943
Max Act: 2.9204. Min Act: -0.1700
Data Index: 1575435 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19