Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.6785. Min Act: -0.1700
Data Index: 4421425 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.6628. Min Act: -0.1700
Data Index: 2231851 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5846. Min Act: -0.1700
Data Index: 8657593 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5533. Min Act: -0.1700
Data Index: 7059153 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5533. Min Act: -0.1700
Data Index: 2845094 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5376. Min Act: -0.1700
Data Index: 3031837 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5063. Min Act: -0.1700
Data Index: 1127418 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.5220. Min Act: -0.1700
Data Index: 5725192 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4906. Min Act: -0.1700
Data Index: 4535241 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4906. Min Act: -0.1700
Data Index: 1085929 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4906. Min Act: -0.1700
Data Index: 2287098 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4750. Min Act: -0.1700
Data Index: 7996161 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4436. Min Act: -0.1700
Data Index: 7615770 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4436. Min Act: -0.1700
Data Index: 925943 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4280. Min Act: -0.1700
Data Index: 8628472 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4280. Min Act: -0.1700
Data Index: 3539807 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4280. Min Act: -0.1700
Data Index: 3966183 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.3966. Min Act: -0.1700
Data Index: 840747 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.4123. Min Act: -0.1700
Data Index: 6717895 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6785. Min Range: -3.6785
Max Act: 3.3966. Min Act: -0.1700
Data Index: 6794199 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19