Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.9132. Min Act: -0.1700
Data Index: 3895340 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.4132. Min Act: -0.1700
Data Index: 6419352 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.4132. Min Act: -0.1700
Data Index: 4859135 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.3507. Min Act: -0.1700
Data Index: 209596 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.2882. Min Act: -0.1700
Data Index: 2024485 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.2257. Min Act: -0.1700
Data Index: 3199628 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.1632. Min Act: -0.1700
Data Index: 5737858 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.1007. Min Act: -0.1700
Data Index: 8320160 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.0382. Min Act: -0.1700
Data Index: 6099141 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.0382. Min Act: -0.1700
Data Index: 6795528 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.0382. Min Act: -0.1699
Data Index: 3345689 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9132. Min Range: -11.9132
Max Act: 11.0382. Min Act: -0.1700
Data Index: 6909447 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 1448650 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 1873011 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 5401060 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 2753631 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9132. Min Act: -0.1700
Data Index: 2499868 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 4915654 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9757. Min Act: -0.1700
Data Index: 4279338 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9132. Min Range: -11.9132
Max Act: 10.9132. Min Act: -0.1700
Data Index: 5728134 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19