Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1215. Min Range: -3.1215
Max Act: 3.1215. Min Act: -0.1700
Data Index: 3312567 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.9320. Min Act: -0.1700
Data Index: 8492909 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.9003. Min Act: -0.1700
Data Index: 2874609 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.9161. Min Act: -0.1700
Data Index: 2542279 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.8209. Min Act: -0.1700
Data Index: 7584458 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.8209. Min Act: -0.1700
Data Index: 3043317 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.8049. Min Act: -0.1700
Data Index: 1849323 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7890. Min Act: -0.1700
Data Index: 8549618 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7890. Min Act: -0.1700
Data Index: 1209243 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7571. Min Act: -0.1700
Data Index: 6232180 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7412. Min Act: -0.1700
Data Index: 1881778 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7571. Min Act: -0.1700
Data Index: 121436 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7571. Min Act: -0.1683
Data Index: 109071 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7412. Min Act: -0.1700
Data Index: 221855 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7412. Min Act: -0.1700
Data Index: 6771750 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7412. Min Act: -0.1700
Data Index: 1679765 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7252. Min Act: -0.1700
Data Index: 6783471 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7252. Min Act: -0.1700
Data Index: 6840550 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7252. Min Act: -0.1700
Data Index: 1536472 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1215. Min Range: -3.1215
Max Act: 2.7571. Min Act: -0.1700
Data Index: 1691829 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19