Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0220. Min Range: -2.0220
Max Act: 2.0220. Min Act: -0.1700
Data Index: 1673434 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.9374. Min Act: -0.1700
Data Index: 5321214 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.9033. Min Act: -0.1700
Data Index: 8270314 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8606. Min Act: -0.1700
Data Index: 7498554 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8521. Min Act: -0.1700
Data Index: 8000347 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8435. Min Act: -0.1700
Data Index: 1181508 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8435. Min Act: -0.1700
Data Index: 7794729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8521. Min Act: -0.1700
Data Index: 2948822 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 7583936 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8435. Min Act: -0.1700
Data Index: 1425158 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8521. Min Act: -0.1700
Data Index: 5741007 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 2474502 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 1942575 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8264. Min Act: -0.1700
Data Index: 7466716 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8178. Min Act: -0.1700
Data Index: 5321210 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 7715990 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 3311944 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8349. Min Act: -0.1700
Data Index: 3180547 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8264. Min Act: -0.1700
Data Index: 3991227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0220. Min Range: -2.0220
Max Act: 1.8264. Min Act: -0.1700
Data Index: 4293751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19