Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.3088. Min Act: -0.1700
Data Index: 8483174 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1202. Min Act: -0.1700
Data Index: 2905508 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1202. Min Act: -0.1700
Data Index: 2945267 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1202. Min Act: -0.1700
Data Index: 4273911 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1202. Min Act: -0.1700
Data Index: 8827727 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1202. Min Act: -0.1700
Data Index: 3651545 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.1044. Min Act: -0.1700
Data Index: 7258635 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0886. Min Act: -0.1700
Data Index: 5857360 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0886. Min Act: -0.1700
Data Index: 3367827 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0571. Min Act: -0.1700
Data Index: 2395533 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0729. Min Act: -0.1700
Data Index: 230124 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0571. Min Act: -0.1700
Data Index: 7989892 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0413. Min Act: -0.1700
Data Index: 2984302 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0413. Min Act: -0.1700
Data Index: 5239129 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0413. Min Act: -0.1700
Data Index: 146032 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0571. Min Act: -0.1700
Data Index: 6359189 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0255. Min Act: -0.1700
Data Index: 218828 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0255. Min Act: -0.1700
Data Index: 4254532 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0255. Min Act: -0.1700
Data Index: 5165431 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3088. Min Range: -3.3088
Max Act: 3.0255. Min Act: -0.1700
Data Index: 513758 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19