Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.5238. Min Act: -0.1700
Data Index: 4380339 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.3676. Min Act: -0.1700
Data Index: 7418315 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.3676. Min Act: -0.1700
Data Index: 4318288 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.3051. Min Act: -0.1700
Data Index: 7159381 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.2738. Min Act: -0.1700
Data Index: 3920659 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.2426. Min Act: -0.1700
Data Index: 5824424 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.2113. Min Act: -0.1700
Data Index: 2222057 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.1176. Min Act: -0.1700
Data Index: 8767996 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0863. Min Act: -0.1700
Data Index: 6152179 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0551. Min Act: -0.1700
Data Index: 5143870 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0551. Min Act: -0.1700
Data Index: 6007869 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0551. Min Act: -0.1700
Data Index: 5143863 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0551. Min Act: -0.1700
Data Index: 8645733 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0238. Min Act: -0.1700
Data Index: 7216853 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0238. Min Act: -0.1700
Data Index: 5143855 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0238. Min Act: -0.1700
Data Index: 627539 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5238. Min Range: -5.5238
Max Act: 4.9926. Min Act: -0.1700
Data Index: 4864153 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5238. Min Range: -5.5238
Max Act: 5.0238. Min Act: -0.1700
Data Index: 1461222 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5238. Min Range: -5.5238
Max Act: 4.9926. Min Act: -0.1700
Data Index: 8588331 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5238. Min Range: -5.5238
Max Act: 4.9926. Min Act: -0.1700
Data Index: 3411913 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19