Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2241. Min Act: -0.0003

Data Index: 1051491 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2042. Min Act: -0.0003

Data Index: 931077 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1895. Min Act: -0.0003

Data Index: 1021828 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1937. Min Act: -0.0003

Data Index: 263100 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1962. Min Act: -0.0003

Data Index: 1198711 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1917. Min Act: -0.0003

Data Index: 8343 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1770. Min Act: -0.0003

Data Index: 1183283 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1768. Min Act: -0.0003

Data Index: 1278986 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1830. Min Act: -0.0003

Data Index: 859166 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1748. Min Act: -0.0002

Data Index: 397079 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1882. Min Act: -0.0003

Data Index: 1197918 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1765. Min Act: -0.0003

Data Index: 408673 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1680. Min Act: -0.0003

Data Index: 882578 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1723. Min Act: -0.0003

Data Index: 255734 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1733. Min Act: -0.0003

Data Index: 845996 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1657. Min Act: -0.0003

Data Index: 54217 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1692. Min Act: -0.0003

Data Index: 1132500 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1694. Min Act: -0.0003

Data Index: 659278 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1621. Min Act: -0.0003

Data Index: 733507 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1729. Min Act: -0.0003

Data Index: 154645 (C4 (Web Text))

Max Activating Token Index: 877