Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6920. Min Range: -8.6920
Max Act: 8.6920. Min Act: -0.1700
Data Index: 5472317 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6920. Min Range: -8.6920
Max Act: 8.1920. Min Act: -0.1700
Data Index: 2675960 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6920. Min Range: -8.6920
Max Act: 8.0045. Min Act: -0.1700
Data Index: 5585694 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6920. Min Range: -8.6920
Max Act: 8.0045. Min Act: -0.1700
Data Index: 416819 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6920. Min Range: -8.6920
Max Act: 8.0045. Min Act: -0.1700
Data Index: 1101309 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.9420. Min Act: -0.1700
Data Index: 7574975 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.8795. Min Act: -0.1700
Data Index: 7929013 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.7857. Min Act: -0.1700
Data Index: 2883474 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.7545. Min Act: -0.1700
Data Index: 5308518 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.7232. Min Act: -0.1700
Data Index: 5710412 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6920. Min Act: -0.1700
Data Index: 4221137 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6920. Min Act: -0.1700
Data Index: 4793959 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6920. Min Act: -0.1700
Data Index: 5751762 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6607. Min Act: -0.1700
Data Index: 7904086 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.5982. Min Act: -0.1700
Data Index: 1161003 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6295. Min Act: -0.1700
Data Index: 3165553 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6295. Min Act: -0.1700
Data Index: 7006611 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.6295. Min Act: -0.1700
Data Index: 1101311 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.5670. Min Act: -0.1700
Data Index: 5580069 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6920. Min Range: -8.6920
Max Act: 7.5670. Min Act: -0.1700
Data Index: 6546458 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19