Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0229. Min Range: -4.0229
Max Act: 4.0229. Min Act: -0.1700
Data Index: 6345777 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.9604. Min Act: -0.1700
Data Index: 3596964 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8666. Min Act: -0.1700
Data Index: 6575646 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 2539759 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8353. Min Act: -0.1700
Data Index: 2970704 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 8340680 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8353. Min Act: -0.1700
Data Index: 3940471 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8666. Min Act: -0.1700
Data Index: 4407209 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8353. Min Act: -0.1700
Data Index: 1258812 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 8340736 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 4765010 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 5678098 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.7727. Min Act: -0.1700
Data Index: 2529529 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 7271351 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 3364944 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8040. Min Act: -0.1700
Data Index: 801343 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.7727. Min Act: -0.1700
Data Index: 4940519 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.7727. Min Act: -0.1700
Data Index: 880808 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.7727. Min Act: -0.1700
Data Index: 2027255 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0229. Min Range: -4.0229
Max Act: 3.8353. Min Act: -0.1700
Data Index: 5976401 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19