Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 7168441 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1943. Min Act: -0.1700
Data Index: 2765052 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1943. Min Act: -0.1700
Data Index: 4831631 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1630. Min Act: -0.1700
Data Index: 8677814 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1630. Min Act: -0.1700
Data Index: 6986785 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1630. Min Act: -0.1700
Data Index: 5250913 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1630. Min Act: -0.1700
Data Index: 5201369 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1630. Min Act: -0.1700
Data Index: 8044296 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1318. Min Act: -0.1700
Data Index: 2573263 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1318. Min Act: -0.1700
Data Index: 2860028 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1318. Min Act: -0.1700
Data Index: 4314143 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1005. Min Act: -0.1700
Data Index: 2765051 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.0693. Min Act: -0.1700
Data Index: 678310 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.1005. Min Act: -0.1700
Data Index: 3142111 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.0380. Min Act: -0.1700
Data Index: 1275242 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.0380. Min Act: -0.1700
Data Index: 2342501 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.0380. Min Act: -0.1700
Data Index: 6986784 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2255. Min Range: -4.2255
Max Act: 4.0068. Min Act: -0.1700
Data Index: 7312054 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2255. Min Range: -4.2255
Max Act: 3.9755. Min Act: -0.1700
Data Index: 2276737 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2255. Min Range: -4.2255
Max Act: 3.9442. Min Act: -0.1700
Data Index: 6200100 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19