Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.2142. Min Act: -0.0001

Data Index: 434569 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1953. Min Act: -0.0000

Data Index: 20635 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1281892 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1834. Min Act: -0.0000

Data Index: 585729 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1779. Min Act: -0.0001

Data Index: 674852 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1059418 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1163539 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1093816 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1292874 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1688. Min Act: -0.0001

Data Index: 803076 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1625. Min Act: -0.0000

Data Index: 134469 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1160768 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1294321 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1620. Min Act: -0.0000

Data Index: 210465 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1203128 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1654. Min Act: -0.0001

Data Index: 505698 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1652. Min Act: -0.0000

Data Index: 30413 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1328206 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1610. Min Act: -0.0000

Data Index: 216078 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.2142. Min Range: -0.2142

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1332210 (C4 (Web Text))

Max Activating Token Index: 350