Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4137 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0682. Min Range: -5.0682
Max Act: 5.0682. Min Act: -0.1700
Data Index: 2882812 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.8494. Min Act: -0.1700
Data Index: 845470 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.6619. Min Act: -0.1700
Data Index: 105544 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.5682. Min Act: -0.1700
Data Index: 6588563 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.5682. Min Act: -0.1700
Data Index: 3433487 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4744. Min Act: -0.1700
Data Index: 4279441 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4432. Min Act: -0.1700
Data Index: 6802486 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4432. Min Act: -0.1700
Data Index: 43326 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 2539698 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1710214 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1434124 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 67021 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3807. Min Act: -0.1700
Data Index: 260333 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 3822324 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1834160 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5713652 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 4612364 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 6347013 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 3943918 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0682. Min Range: -5.0682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 915798 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19