Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1234. Min Range: -8.1234
Max Act: 8.1234. Min Act: -0.1700
Data Index: 6867010 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.6234. Min Act: -0.1700
Data Index: 1178901 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.6547. Min Act: -0.1700
Data Index: 8420112 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.6547. Min Act: -0.1700
Data Index: 7708635 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7071012 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.5922. Min Act: -0.1700
Data Index: 8641513 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.5609. Min Act: -0.1700
Data Index: 1442327 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.5609. Min Act: -0.1700
Data Index: 1384713 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.5609. Min Act: -0.1700
Data Index: 991722 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4984. Min Act: -0.1700
Data Index: 8454053 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4672. Min Act: -0.1700
Data Index: 7959083 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4984. Min Act: -0.1700
Data Index: 5912792 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3671294 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3082533 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4672. Min Act: -0.1700
Data Index: 4980748 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.3734. Min Act: -0.1700
Data Index: 3257165 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4047. Min Act: -0.1700
Data Index: 3816921 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.4359. Min Act: -0.1700
Data Index: 1185833 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.3734. Min Act: -0.1700
Data Index: 604569 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1234. Min Range: -8.1234
Max Act: 7.3734. Min Act: -0.1700
Data Index: 2827847 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19