Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1808 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.9391. Min Act: -0.1700
Data Index: 1043718 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.9078. Min Act: -0.1700
Data Index: 6035116 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.8766. Min Act: -0.1700
Data Index: 5599178 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.8453. Min Act: -0.1700
Data Index: 5838248 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.8141. Min Act: -0.1700
Data Index: 6469100 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.8141. Min Act: -0.1700
Data Index: 7101900 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.8141. Min Act: -0.1700
Data Index: 2080067 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.7828. Min Act: -0.1700
Data Index: 5381298 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.7516. Min Act: -0.1700
Data Index: 1903997 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7945659 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.7516. Min Act: -0.1700
Data Index: 3407138 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.6891. Min Act: -0.1700
Data Index: 7276148 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.6578. Min Act: -0.1700
Data Index: 60068 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.5953. Min Act: -0.1700
Data Index: 7594800 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.6266. Min Act: -0.1700
Data Index: 4819475 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.5328. Min Act: -0.1700
Data Index: 2924776 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.5328. Min Act: -0.1700
Data Index: 1473273 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.5328. Min Act: -0.1700
Data Index: 4885657 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.5016. Min Act: -0.1700
Data Index: 2994336 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9391. Min Range: -6.9391
Max Act: 6.4391. Min Act: -0.1700
Data Index: 1628767 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19