Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5280 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4887121 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.8084. Min Act: -0.1700
Data Index: 4467459 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7928. Min Act: -0.1700
Data Index: 2605345 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7771. Min Act: -0.1700
Data Index: 6098229 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7458. Min Act: -0.1700
Data Index: 2147327 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7458. Min Act: -0.1700
Data Index: 622189 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7615. Min Act: -0.1700
Data Index: 27570 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 4429003 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 6378888 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 5471212 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 7508911 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 7797364 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7302. Min Act: -0.1700
Data Index: 936146 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7146. Min Act: -0.1700
Data Index: 7108878 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.7146. Min Act: -0.1700
Data Index: 7211587 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.6989. Min Act: -0.1700
Data Index: 663123 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.6989. Min Act: -0.1700
Data Index: 1656819 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.6989. Min Act: -0.1700
Data Index: 4962900 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.6989. Min Act: -0.1700
Data Index: 1754218 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8084. Min Range: -3.8084
Max Act: 3.6989. Min Act: -0.1700
Data Index: 3909427 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19