Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2151 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.6501. Min Act: -0.1700
Data Index: 2551203 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.6189. Min Act: -0.1700
Data Index: 7962226 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.5564. Min Act: -0.1700
Data Index: 2075719 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.5564. Min Act: -0.1700
Data Index: 6807641 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.5251. Min Act: -0.1700
Data Index: 4414100 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4626. Min Act: -0.1700
Data Index: 2551189 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4626. Min Act: -0.1700
Data Index: 4019402 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4626. Min Act: -0.1700
Data Index: 5645798 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4314. Min Act: -0.1700
Data Index: 3767021 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4314. Min Act: -0.1700
Data Index: 1553880 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4314. Min Act: -0.1700
Data Index: 377178 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4314. Min Act: -0.1700
Data Index: 2075725 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.3688. Min Act: -0.1700
Data Index: 4600917 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4001. Min Act: -0.1700
Data Index: 5961094 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4001. Min Act: -0.1700
Data Index: 813996 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.4001. Min Act: -0.1700
Data Index: 2280270 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.3376. Min Act: -0.1700
Data Index: 1887765 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.3688. Min Act: -0.1700
Data Index: 4019401 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.3688. Min Act: -0.1700
Data Index: 7419622 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6501. Min Range: -4.6501
Max Act: 4.3688. Min Act: -0.1700
Data Index: 35391 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19