Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3362. Min Range: -10.3362
Max Act: 10.3362. Min Act: -0.1700
Data Index: 7327456 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.8362. Min Act: -0.1700
Data Index: 6413224 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.8362. Min Act: -0.1700
Data Index: 2719068 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.7737. Min Act: -0.1700
Data Index: 4154888 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.7737. Min Act: -0.1700
Data Index: 7404827 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.7112. Min Act: -0.1700
Data Index: 3919791 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.5862. Min Act: -0.1700
Data Index: 8270802 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.5237. Min Act: -0.1700
Data Index: 7026954 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.4612. Min Act: -0.1700
Data Index: 2057699 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.4612. Min Act: -0.1700
Data Index: 898579 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3987. Min Act: -0.1700
Data Index: 6702624 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.4612. Min Act: -0.1700
Data Index: 8069922 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3987. Min Act: -0.1700
Data Index: 4697027 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3987. Min Act: -0.1700
Data Index: 4831042 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3362. Min Act: -0.1700
Data Index: 1550375 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3362. Min Act: -0.1700
Data Index: 3008448 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3362. Min Act: -0.1700
Data Index: 4648772 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.3987. Min Act: -0.1700
Data Index: 378986 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.2737. Min Act: -0.1700
Data Index: 6935067 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3362. Min Range: -10.3362
Max Act: 9.2737. Min Act: -0.1700
Data Index: 3881439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19