Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1534 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.6317. Min Act: -0.1700
Data Index: 1683619 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.6473. Min Act: -0.1700
Data Index: 7093894 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.6160. Min Act: -0.1700
Data Index: 549989 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.6004. Min Act: -0.1700
Data Index: 2896032 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5221. Min Act: -0.1700
Data Index: 5382993 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5064. Min Act: -0.1700
Data Index: 7344102 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4908. Min Act: -0.1700
Data Index: 6654239 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4438. Min Act: -0.1700
Data Index: 8269125 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4281. Min Act: -0.1700
Data Index: 1663677 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3967. Min Act: -0.1700
Data Index: 1313151 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3967. Min Act: -0.1700
Data Index: 6111219 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4124. Min Act: -0.1700
Data Index: 2376989 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3967. Min Act: -0.1700
Data Index: 2354119 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4124. Min Act: -0.1700
Data Index: 8249849 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3811. Min Act: -0.1700
Data Index: 1654993 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3811. Min Act: -0.1700
Data Index: 4280787 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3654. Min Act: -0.1700
Data Index: 4198450 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3654. Min Act: -0.1700
Data Index: 2775432 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3497. Min Act: -0.1700
Data Index: 7450136 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.3654. Min Act: -0.1700
Data Index: 4342374 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19