Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.8571. Min Act: -0.1700
Data Index: 5009116 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.8258. Min Act: -0.1700
Data Index: 3560407 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.7008. Min Act: -0.1700
Data Index: 1653986 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.6383. Min Act: -0.1700
Data Index: 3560406 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.5758. Min Act: -0.1700
Data Index: 6401533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.6071. Min Act: -0.1700
Data Index: 263124 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.5758. Min Act: -0.1700
Data Index: 4184976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.5758. Min Act: -0.1700
Data Index: 5660905 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.4821. Min Act: -0.1700
Data Index: 4315621 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.4821. Min Act: -0.1700
Data Index: 1653982 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.5133. Min Act: -0.1700
Data Index: 6480933 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.4508. Min Act: -0.1700
Data Index: 7968609 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.4196. Min Act: -0.1700
Data Index: 6588256 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 4259399 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 6964854 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 4673355 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 5340684 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 7549170 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 7400672 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8571. Min Range: -6.8571
Max Act: 6.3883. Min Act: -0.1700
Data Index: 6356152 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19