Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3732. Min Range: -4.3732

Max Act: 4.3732. Min Act: -0.0000

Data Index: 231726 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.9936. Min Act: -0.0000

Data Index: 1160968 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.6559. Min Act: -0.0000

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.1662. Min Act: -0.0000

Data Index: 100689 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.0127. Min Act: -0.0000

Data Index: 1315714 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.3332. Min Act: -0.0000

Data Index: 1100782 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 4.3732. Min Range: -4.3732

Max Act: 3.0311. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.9629. Min Act: -0.0000

Data Index: 1060171 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.8125. Min Act: -0.0000

Data Index: 1190020 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.7494. Min Act: -0.0000

Data Index: 1310979 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.8203. Min Act: -0.0000

Data Index: 1224139 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.9915. Min Act: -0.0000

Data Index: 477425 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.8694. Min Act: -0.0000

Data Index: 488618 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.6156. Min Act: -0.0000

Data Index: 337457 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.7977. Min Act: -0.0000

Data Index: 936476 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.7678. Min Act: -0.0000

Data Index: 1076213 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1161839 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.7430. Min Act: -0.0000

Data Index: 566646 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.6174. Min Act: -0.0000

Data Index: 370313 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 4.3732. Min Range: -4.3732

Max Act: 2.7268. Min Act: -0.0000

Data Index: 1247860 (C4 (Web Text))

Max Activating Token Index: 205