Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 267 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.5173. Min Act: -0.1700
Data Index: 1298258 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.5173. Min Act: -0.1700
Data Index: 7973693 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.5016. Min Act: -0.1700
Data Index: 6952287 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4860. Min Act: -0.1700
Data Index: 8299225 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4860. Min Act: -0.1700
Data Index: 4998295 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4860. Min Act: -0.1700
Data Index: 5820063 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4703. Min Act: -0.1700
Data Index: 5108075 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4860. Min Act: -0.1700
Data Index: 1723326 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4390. Min Act: -0.1700
Data Index: 8272547 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.4390. Min Act: -0.1700
Data Index: 4977974 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3763. Min Act: -0.1700
Data Index: 7017612 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3763. Min Act: -0.1700
Data Index: 8272546 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3606. Min Act: -0.1700
Data Index: 8331276 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3449. Min Act: -0.1700
Data Index: 5695365 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3606. Min Act: -0.1700
Data Index: 5791969 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3606. Min Act: -0.1700
Data Index: 8272548 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3449. Min Act: -0.1700
Data Index: 5820064 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3449. Min Act: -0.1700
Data Index: 6019412 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3449. Min Act: -0.1700
Data Index: 6286030 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5173. Min Range: -3.5173
Max Act: 3.3449. Min Act: -0.1700
Data Index: 5604996 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19