Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.5240. Min Act: -0.1700
Data Index: 4008328 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4928. Min Act: -0.1700
Data Index: 3800299 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4928. Min Act: -0.1700
Data Index: 5618636 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 3139878 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 2653014 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 465041 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 8660064 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 2595948 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4098677 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 2485376 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 3003196 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 8096109 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4615. Min Act: -0.1700
Data Index: 1972631 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4632055 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4085174 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.3990. Min Act: -0.1700
Data Index: 7518660 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 2657759 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.3990. Min Act: -0.1700
Data Index: 6608968 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.4303. Min Act: -0.1700
Data Index: 6428908 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5240. Min Range: -4.5240
Max Act: 4.3678. Min Act: -0.1700
Data Index: 6177654 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19