Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 486 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.9847. Min Act: -0.1700
Data Index: 2624418 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8597. Min Act: -0.1700
Data Index: 490109 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8909. Min Act: -0.1700
Data Index: 7418796 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8284. Min Act: -0.1700
Data Index: 687340 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8284. Min Act: -0.1700
Data Index: 7639955 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8284. Min Act: -0.1700
Data Index: 6230647 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.8284. Min Act: -0.1700
Data Index: 551737 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.7972. Min Act: -0.1700
Data Index: 6292891 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.7659. Min Act: -0.1700
Data Index: 114682 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.7347. Min Act: -0.1700
Data Index: 8776340 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.7034. Min Act: -0.1700
Data Index: 2325577 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6409. Min Act: -0.1700
Data Index: 993235 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6409. Min Act: -0.1700
Data Index: 3076819 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.7034. Min Act: -0.1700
Data Index: 3347198 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6409. Min Act: -0.1700
Data Index: 7954971 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6097. Min Act: -0.1700
Data Index: 3045554 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6722. Min Act: -0.1700
Data Index: 2311228 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6409. Min Act: -0.1700
Data Index: 3291074 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6097. Min Act: -0.1700
Data Index: 2561036 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9847. Min Range: -4.9847
Max Act: 4.6097. Min Act: -0.1700
Data Index: 512908 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19