Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.5736. Min Act: -0.1700
Data Index: 186647 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4953. Min Act: -0.1700
Data Index: 772281 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4640. Min Act: -0.1700
Data Index: 1626967 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4483. Min Act: -0.1700
Data Index: 4063500 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4169. Min Act: -0.1700
Data Index: 3627034 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4326. Min Act: -0.1700
Data Index: 1347242 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4169. Min Act: -0.1700
Data Index: 3627035 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4169. Min Act: -0.1700
Data Index: 2789516 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4169. Min Act: -0.1700
Data Index: 4597951 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4013. Min Act: -0.1700
Data Index: 1347243 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.4169. Min Act: -0.1700
Data Index: 2733569 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3542. Min Act: -0.1700
Data Index: 4713982 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3542. Min Act: -0.1700
Data Index: 81103 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3699. Min Act: -0.1700
Data Index: 29281 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3699. Min Act: -0.1700
Data Index: 1603069 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3385. Min Act: -0.1700
Data Index: 531721 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3542. Min Act: -0.1700
Data Index: 3027320 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3542. Min Act: -0.1700
Data Index: 2830636 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3542. Min Act: -0.1700
Data Index: 1636079 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5736. Min Range: -3.5736
Max Act: 3.3228. Min Act: -0.1700
Data Index: 2830227 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19