Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.5057. Min Act: -0.1700
Data Index: 3164308 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.4120. Min Act: -0.1700
Data Index: 1327073 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.3807. Min Act: -0.1700
Data Index: 4239460 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.3807. Min Act: -0.1700
Data Index: 6684645 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.3807. Min Act: -0.1700
Data Index: 5647040 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.3182. Min Act: -0.1700
Data Index: 4459394 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2870. Min Act: -0.1700
Data Index: 4999 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2870. Min Act: -0.1700
Data Index: 5899906 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2870. Min Act: -0.1700
Data Index: 2433087 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2557. Min Act: -0.1700
Data Index: 7513418 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2557. Min Act: -0.1700
Data Index: 1425399 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2557. Min Act: -0.1700
Data Index: 1450605 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2245. Min Act: -0.1700
Data Index: 6755010 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2557. Min Act: -0.1700
Data Index: 2703722 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2245. Min Act: -0.1700
Data Index: 1749833 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2245. Min Act: -0.1700
Data Index: 6969223 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2245. Min Act: -0.1700
Data Index: 3373912 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2557. Min Act: -0.1700
Data Index: 3848612 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.2245. Min Act: -0.1700
Data Index: 4378099 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5057. Min Range: -6.5057
Max Act: 6.1932. Min Act: -0.1700
Data Index: 7143469 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19