Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 308 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0117. Min Range: -4.0117
Max Act: 4.0117. Min Act: -0.1700
Data Index: 5152648 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.9491. Min Act: -0.1700
Data Index: 5459146 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.9179. Min Act: -0.1700
Data Index: 4082154 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8866. Min Act: -0.1700
Data Index: 410391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8866. Min Act: -0.1700
Data Index: 7057738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8866. Min Act: -0.1700
Data Index: 2150309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2026155 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6025139 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1775485 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1277534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6682270 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 527337 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6626041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 5906351 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4704366 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4483294 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 2134447 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4418056 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7928. Min Act: -0.1700
Data Index: 654606 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7615. Min Act: -0.1700
Data Index: 5249762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19