Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 351 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1738. Min Act: -0.1700
Data Index: 8572828 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.9530. Min Act: -0.1700
Data Index: 1303889 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.9054. Min Act: -0.1700
Data Index: 6610952 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.9530. Min Act: -0.1700
Data Index: 4590989 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.8419. Min Act: -0.1700
Data Index: 6608791 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.8101. Min Act: -0.1700
Data Index: 5922377 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.8260. Min Act: -0.1700
Data Index: 7147692 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.8101. Min Act: -0.1700
Data Index: 6599347 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7783. Min Act: -0.1700
Data Index: 4311944 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7623. Min Act: -0.1700
Data Index: 6973801 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7783. Min Act: -0.1700
Data Index: 1633502 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7623. Min Act: -0.1700
Data Index: 4049658 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7783. Min Act: -0.1700
Data Index: 1882368 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7623. Min Act: -0.1700
Data Index: 824656 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7304. Min Act: -0.1700
Data Index: 5485979 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7464. Min Act: -0.1700
Data Index: 793846 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7304. Min Act: -0.1700
Data Index: 7024697 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7464. Min Act: -0.1700
Data Index: 3392705 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7304. Min Act: -0.1700
Data Index: 7064801 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1738. Min Range: -3.1738
Max Act: 2.7464. Min Act: -0.1700
Data Index: 8245333 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19