Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6504. Min Act: -0.1700
Data Index: 2011407 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 5365618 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1454234 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 8520667 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 2161821 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 6041689 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 7644491 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 6195580 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6504. Min Act: -0.1700
Data Index: 842067 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6191. Min Act: -0.1700
Data Index: 4894288 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5879. Min Act: -0.1700
Data Index: 2980472 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5879. Min Act: -0.1700
Data Index: 942102 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5879. Min Act: -0.1700
Data Index: 76024 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5879. Min Act: -0.1700
Data Index: 8683522 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5879. Min Act: -0.1700
Data Index: 5806329 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5566. Min Act: -0.1700
Data Index: 7111210 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5566. Min Act: -0.1700
Data Index: 6565915 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5254. Min Act: -0.1700
Data Index: 7763519 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5254. Min Act: -0.1700
Data Index: 6190028 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4941. Min Act: -0.1700
Data Index: 2198773 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19