Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.8312. Min Act: -0.1700
Data Index: 7590161 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.8312. Min Act: -0.1700
Data Index: 7180794 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2509028 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.3625. Min Act: -0.1700
Data Index: 203039 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2687. Min Act: -0.1700
Data Index: 1602429 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2375. Min Act: -0.1700
Data Index: 4113931 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2687. Min Act: -0.1700
Data Index: 1075214 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2375. Min Act: -0.1700
Data Index: 7741829 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2062. Min Act: -0.1700
Data Index: 3751278 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2062. Min Act: -0.1700
Data Index: 7836187 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2375. Min Act: -0.1700
Data Index: 2445770 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.2062. Min Act: -0.1700
Data Index: 2155847 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.1750. Min Act: -0.1700
Data Index: 1421381 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.1750. Min Act: -0.1700
Data Index: 889105 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.1750. Min Act: -0.1700
Data Index: 8828205 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.1437. Min Act: -0.1700
Data Index: 8331110 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.0812. Min Act: -0.1700
Data Index: 7832181 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8420836 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.0500. Min Act: -0.1700
Data Index: 394689 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8312. Min Range: -6.8312
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8584430 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19