Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.9859. Min Act: -0.1700
Data Index: 7050878 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7984. Min Act: -0.1700
Data Index: 2125692 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7046. Min Act: -0.1700
Data Index: 2912732 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6421. Min Act: -0.1700
Data Index: 4559557 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6109. Min Act: -0.1700
Data Index: 5686168 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6421. Min Act: -0.1700
Data Index: 6609293 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.5796. Min Act: -0.1700
Data Index: 8470170 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.5796. Min Act: -0.1700
Data Index: 3199487 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.5484. Min Act: -0.1700
Data Index: 407092 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.5171. Min Act: -0.1700
Data Index: 3294608 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.5171. Min Act: -0.1700
Data Index: 5095318 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4859. Min Act: -0.1700
Data Index: 2415533 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4546. Min Act: -0.1700
Data Index: 1243525 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4859. Min Act: -0.1700
Data Index: 1769495 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5122558 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4234. Min Act: -0.1700
Data Index: 2782736 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.3921. Min Act: -0.1700
Data Index: 4266031 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.4234. Min Act: -0.1700
Data Index: 4866953 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.3921. Min Act: -0.1700
Data Index: 3960837 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.3921. Min Act: -0.1700
Data Index: 1182388 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19