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

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

Neuron 2180 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2203. Min Act: -0.0002

Data Index: 1173552 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2180. Min Act: -0.0002

Data Index: 686599 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2093. Min Act: -0.0003

Data Index: 458913 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1966. Min Act: -0.0003

Data Index: 990870 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1940. Min Act: -0.0002

Data Index: 686666 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1926. Min Act: -0.0003

Data Index: 81739 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1865. Min Act: -0.0003

Data Index: 1152341 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1858. Min Act: -0.0003

Data Index: 505261 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1740. Min Act: -0.0002

Data Index: 1033628 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1674. Min Act: -0.0003

Data Index: 773199 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1615. Min Act: -0.0002

Data Index: 984421 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1659. Min Act: -0.0003

Data Index: 1035670 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1595. Min Act: -0.0003

Data Index: 579094 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1233950 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1538. Min Act: -0.0003

Data Index: 408761 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1583. Min Act: -0.0003

Data Index: 1169154 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1578. Min Act: -0.0003

Data Index: 1261786 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1575. Min Act: -0.0003

Data Index: 286396 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1553. Min Act: -0.0002

Data Index: 701833 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1496. Min Act: -0.0003

Data Index: 707216 (C4 (Web Text))

Max Activating Token Index: 204