Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.9595. Min Act: -0.1700
Data Index: 3447295 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1398661 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.7095. Min Act: -0.1700
Data Index: 4525696 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6783. Min Act: -0.1700
Data Index: 4318531 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.7095. Min Act: -0.1700
Data Index: 8533380 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6470. Min Act: -0.1700
Data Index: 6262157 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6470. Min Act: -0.1700
Data Index: 4084435 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6470. Min Act: -0.1700
Data Index: 7521636 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6158. Min Act: -0.1700
Data Index: 1129330 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6158. Min Act: -0.1700
Data Index: 8448795 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5845. Min Act: -0.1700
Data Index: 4156597 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6470. Min Act: -0.1700
Data Index: 5653701 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.6158. Min Act: -0.1700
Data Index: 4242195 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5533. Min Act: -0.1700
Data Index: 8668180 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5533. Min Act: -0.1700
Data Index: 1096854 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2156278 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5220. Min Act: -0.1700
Data Index: 3787064 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5220. Min Act: -0.1700
Data Index: 6924049 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2356095 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9595. Min Range: -5.9595
Max Act: 5.5220. Min Act: -0.1700
Data Index: 6338533 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19