Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.8600. Min Act: -0.1700
Data Index: 848830 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.7975. Min Act: -0.1700
Data Index: 5029799 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.7350. Min Act: -0.1700
Data Index: 5839876 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.7350. Min Act: -0.1700
Data Index: 6100360 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.7037. Min Act: -0.1700
Data Index: 3442144 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.6412. Min Act: -0.1700
Data Index: 5993953 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.6725. Min Act: -0.1700
Data Index: 8313995 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1831921 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5475. Min Act: -0.1700
Data Index: 764148 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 3106853 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1604409 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 5684068 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 3171911 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 2933098 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.5162. Min Act: -0.1700
Data Index: 3501618 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.4850. Min Act: -0.1700
Data Index: 7571487 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.4850. Min Act: -0.1700
Data Index: 3436114 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.4850. Min Act: -0.1700
Data Index: 2110025 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.4225. Min Act: -0.1700
Data Index: 890398 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8600. Min Range: -4.8600
Max Act: 4.4850. Min Act: -0.1700
Data Index: 7954212 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19