Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.6816. Min Act: -0.1700
Data Index: 4540330 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.6504. Min Act: -0.1700
Data Index: 3320410 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.5566. Min Act: -0.1700
Data Index: 578212 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4941. Min Act: -0.1700
Data Index: 209160 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4629. Min Act: -0.1700
Data Index: 6601865 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4316. Min Act: -0.1700
Data Index: 5223949 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4316. Min Act: -0.1700
Data Index: 1906817 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 4926297 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4316. Min Act: -0.1700
Data Index: 3820927 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1731525 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 7644698 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1915931 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 348499 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 5406112 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1828542 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.3379. Min Act: -0.1700
Data Index: 198184 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.3691. Min Act: -0.1700
Data Index: 5789437 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.4004. Min Act: -0.1700
Data Index: 5922349 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.3066. Min Act: -0.1700
Data Index: 5338897 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6816. Min Range: -4.6816
Max Act: 4.3066. Min Act: -0.1700
Data Index: 5856653 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19