Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5469 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0567. Min Range: -3.0567
Max Act: 3.0567. Min Act: -0.1700
Data Index: 935662 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0567. Min Range: -3.0567
Max Act: 3.0409. Min Act: -0.1700
Data Index: 4506053 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0567. Min Range: -3.0567
Max Act: 3.0251. Min Act: -0.1700
Data Index: 465567 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9619. Min Act: -0.1700
Data Index: 4137163 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9619. Min Act: -0.1700
Data Index: 210583 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9302. Min Act: -0.1700
Data Index: 7149512 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9302. Min Act: -0.1700
Data Index: 769121 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9302. Min Act: -0.1700
Data Index: 3625074 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9302. Min Act: -0.1700
Data Index: 1500564 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9143. Min Act: -0.1700
Data Index: 4947178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9143. Min Act: -0.1700
Data Index: 4677037 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9143. Min Act: -0.1700
Data Index: 2542559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.9143. Min Act: -0.1700
Data Index: 1465189 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8985. Min Act: -0.1700
Data Index: 4369825 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8826. Min Act: -0.1700
Data Index: 7095447 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8826. Min Act: -0.1700
Data Index: 2629810 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8826. Min Act: -0.1700
Data Index: 7244924 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8668. Min Act: -0.1700
Data Index: 3232104 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8668. Min Act: -0.1700
Data Index: 5086143 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0567. Min Range: -3.0567
Max Act: 2.8668. Min Act: -0.1700
Data Index: 5771715 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19