Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 994 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.3888. Min Act: -0.1700
Data Index: 7638214 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.3260. Min Act: -0.1700
Data Index: 5750834 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1689. Min Act: -0.1700
Data Index: 4278838 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1846. Min Act: -0.1700
Data Index: 3839048 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1846. Min Act: -0.1700
Data Index: 8780985 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1689. Min Act: -0.1700
Data Index: 3017805 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1217. Min Act: -0.1700
Data Index: 5134564 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1059. Min Act: -0.1700
Data Index: 554764 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0901. Min Act: -0.1700
Data Index: 5854699 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0901. Min Act: -0.1700
Data Index: 7297995 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.1059. Min Act: -0.1700
Data Index: 3734344 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0901. Min Act: -0.1700
Data Index: 770853 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0586. Min Act: -0.1700
Data Index: 8827498 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0901. Min Act: -0.1700
Data Index: 2922043 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0744. Min Act: -0.1700
Data Index: 1660587 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0586. Min Act: -0.1700
Data Index: 5764722 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0744. Min Act: -0.1700
Data Index: 2617475 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0586. Min Act: -0.1700
Data Index: 799367 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0428. Min Act: -0.1700
Data Index: 2170513 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3888. Min Range: -3.3888
Max Act: 3.0744. Min Act: -0.1700
Data Index: 1628054 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19