Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 13.7243. Min Range: -13.7243
Max Act: 13.7243. Min Act: -0.1700
Data Index: 63007 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.7243. Min Range: -13.7243
Max Act: 13.1618. Min Act: -0.1700
Data Index: 63006 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.8493. Min Act: -0.1700
Data Index: 63008 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.5368. Min Act: -0.1700
Data Index: 4292062 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.4743. Min Act: -0.1700
Data Index: 63009 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.3493. Min Act: -0.1700
Data Index: 63011 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.3493. Min Act: -0.1700
Data Index: 63010 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.1618. Min Act: -0.1700
Data Index: 63012 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.7243. Min Range: -13.7243
Max Act: 12.1618. Min Act: -0.1700
Data Index: 612756 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.9743. Min Act: -0.1700
Data Index: 3162422 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.9743. Min Act: -0.1700
Data Index: 5194026 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.9743. Min Act: -0.1700
Data Index: 4292070 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.7868. Min Act: -0.1700
Data Index: 5710726 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.7243. Min Act: -0.1700
Data Index: 63013 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.7868. Min Act: -0.1700
Data Index: 63017 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.7243. Min Act: -0.1700
Data Index: 4247558 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.6618. Min Act: -0.1700
Data Index: 4553802 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.6618. Min Act: -0.1700
Data Index: 3904099 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.5368. Min Act: -0.1700
Data Index: 1673578 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.7243. Min Range: -13.7243
Max Act: 11.5368. Min Act: -0.1700
Data Index: 63014 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19