Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.7357. Min Act: -0.1700
Data Index: 909225 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.6107. Min Act: -0.1700
Data Index: 233499 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.6732. Min Act: -0.1700
Data Index: 6321655 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.4857. Min Act: -0.1700
Data Index: 8050151 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.4857. Min Act: -0.1700
Data Index: 1915726 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7923040 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.4857. Min Act: -0.1700
Data Index: 3308370 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.3607. Min Act: -0.1700
Data Index: 1693398 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.3607. Min Act: -0.1700
Data Index: 1020523 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.3607. Min Act: -0.1700
Data Index: 469337 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.3607. Min Act: -0.1700
Data Index: 1676464 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2982. Min Act: -0.1700
Data Index: 3532969 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2982. Min Act: -0.1700
Data Index: 1152858 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2982. Min Act: -0.1700
Data Index: 4220868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1700
Data Index: 1745229 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1700
Data Index: 2569543 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1700
Data Index: 582682 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1699
Data Index: 3796301 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1700
Data Index: 5421108 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7357. Min Range: -7.7357
Max Act: 7.2357. Min Act: -0.1700
Data Index: 6566908 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19