Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.3274. Min Act: -0.1700
Data Index: 6672167 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2649. Min Act: -0.1699
Data Index: 4802701 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2336. Min Act: -0.1700
Data Index: 2500450 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7605947 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7866168 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2024. Min Act: -0.1700
Data Index: 3049317 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.2024. Min Act: -0.1700
Data Index: 4214301 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1711. Min Act: -0.1700
Data Index: 2703586 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1711. Min Act: -0.1700
Data Index: 5412747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1711. Min Act: -0.1700
Data Index: 2430119 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1711. Min Act: -0.1700
Data Index: 8376405 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1711. Min Act: -0.1700
Data Index: 8770634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1086. Min Act: -0.1700
Data Index: 8070193 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 4245084 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 7659624 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 4840275 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 8124861 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 7651588 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 7587329 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 5450252 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19