Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.4366. Min Act: -0.1700
Data Index: 7824614 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.4054. Min Act: -0.1700
Data Index: 6920412 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.4054. Min Act: -0.1700
Data Index: 2207728 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3741. Min Act: -0.1700
Data Index: 8241564 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3741. Min Act: -0.1700
Data Index: 6363999 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 6323816 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 8269117 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 1434057 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 3586131 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 1893027 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 5326463 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3429. Min Act: -0.1700
Data Index: 6826736 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3741. Min Act: -0.1700
Data Index: 1243597 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 3170157 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 5605670 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 2347411 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 1668760 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 6618048 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 6735699 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4366. Min Range: -5.4366
Max Act: 5.3116. Min Act: -0.1700
Data Index: 5053681 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19