Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6364 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.6336. Min Act: -0.1700
Data Index: 5650406 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.4461. Min Act: -0.1700
Data Index: 1582119 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.3836. Min Act: -0.1700
Data Index: 7955118 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.0398. Min Act: -0.1700
Data Index: 4063409 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.0711. Min Act: -0.1700
Data Index: 289003 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.0398. Min Act: -0.1700
Data Index: 2705925 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6336. Min Range: -5.6336
Max Act: 5.0086. Min Act: -0.1700
Data Index: 8414887 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9773. Min Act: -0.1700
Data Index: 6271412 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 3727606 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 176127 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 5025142 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9773. Min Act: -0.1700
Data Index: 4373736 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 6870555 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 1961200 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9773. Min Act: -0.1700
Data Index: 4156151 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9148. Min Act: -0.1700
Data Index: 2073556 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.8836. Min Act: -0.1700
Data Index: 2414371 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.8836. Min Act: -0.1700
Data Index: 37975 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3066894 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6336. Min Range: -5.6336
Max Act: 4.9148. Min Act: -0.1700
Data Index: 1566845 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19