Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 682 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4678. Min Range: -6.4678
Max Act: 6.4678. Min Act: -0.1700
Data Index: 3093715 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4678. Min Range: -6.4678
Max Act: 6.1866. Min Act: -0.1700
Data Index: 5183949 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4678. Min Range: -6.4678
Max Act: 6.1241. Min Act: -0.1700
Data Index: 7772746 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4678. Min Range: -6.4678
Max Act: 6.0928. Min Act: -0.1700
Data Index: 6942557 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4678. Min Range: -6.4678
Max Act: 6.0616. Min Act: -0.1700
Data Index: 4842373 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9991. Min Act: -0.1700
Data Index: 1109711 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9991. Min Act: -0.1700
Data Index: 6445048 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9678. Min Act: -0.1700
Data Index: 4799805 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9678. Min Act: -0.1700
Data Index: 3257694 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9678. Min Act: -0.1700
Data Index: 7750770 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7675179 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7923880 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8741. Min Act: -0.1700
Data Index: 4600097 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8428. Min Act: -0.1700
Data Index: 5551443 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8428. Min Act: -0.1700
Data Index: 2794678 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8428. Min Act: -0.1700
Data Index: 3798672 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8116. Min Act: -0.1700
Data Index: 3275798 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8116. Min Act: -0.1700
Data Index: 6001742 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.7803. Min Act: -0.1700
Data Index: 5450088 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4678. Min Range: -6.4678
Max Act: 5.8116. Min Act: -0.1700
Data Index: 6748232 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19