Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8765933 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.6352. Min Act: -0.1700
Data Index: 8194602 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.6352. Min Act: -0.1700
Data Index: 7596900 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.5414. Min Act: -0.1700
Data Index: 7753452 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.5414. Min Act: -0.1700
Data Index: 938694 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.5414. Min Act: -0.1700
Data Index: 1505340 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.5102. Min Act: -0.1700
Data Index: 3109664 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5500751 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.5102. Min Act: -0.1700
Data Index: 2018104 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5131598 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4477. Min Act: -0.1700
Data Index: 3506283 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4477. Min Act: -0.1700
Data Index: 3875791 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4789. Min Act: -0.1700
Data Index: 802612 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4789. Min Act: -0.1700
Data Index: 4482899 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3314913 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4477. Min Act: -0.1700
Data Index: 2057558 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.4477. Min Act: -0.1700
Data Index: 4561256 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.3852. Min Act: -0.1700
Data Index: 3533534 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.3852. Min Act: -0.1700
Data Index: 5363470 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6977. Min Range: -5.6977
Max Act: 5.3852. Min Act: -0.1700
Data Index: 6292591 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19