Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.8828. Min Act: -0.1700
Data Index: 6509160 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.7891. Min Act: -0.1700
Data Index: 3833975 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.6953. Min Act: -0.1700
Data Index: 795507 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.6328. Min Act: -0.1700
Data Index: 2616079 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.6016. Min Act: -0.1700
Data Index: 1229040 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.6016. Min Act: -0.1700
Data Index: 7204712 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.5703. Min Act: -0.1700
Data Index: 3503018 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.5391. Min Act: -0.1700
Data Index: 6611568 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.5078. Min Act: -0.1700
Data Index: 3007483 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4453. Min Act: -0.1700
Data Index: 7849248 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.5078. Min Act: -0.1700
Data Index: 2523812 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.5078. Min Act: -0.1700
Data Index: 6946902 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1292125 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5432755 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.3828. Min Act: -0.1700
Data Index: 355471 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5161115 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 6627918 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 805314 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4141. Min Act: -0.1700
Data Index: 91356 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8828. Min Range: -4.8828
Max Act: 4.4453. Min Act: -0.1700
Data Index: 6040108 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19