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

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

Neuron 2711 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2258. Min Act: -0.0003

Data Index: 457746 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2252. Min Act: -0.0002

Data Index: 257364 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2146. Min Act: -0.0002

Data Index: 41310 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1192006 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2147. Min Act: -0.0003

Data Index: 1264767 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2163. Min Act: -0.0002

Data Index: 715157 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2092. Min Act: -0.0002

Data Index: 484834 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1980. Min Act: -0.0002

Data Index: 130051 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1954. Min Act: -0.0002

Data Index: 317778 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1935. Min Act: -0.0002

Data Index: 593973 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1931. Min Act: -0.0002

Data Index: 51146 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1896. Min Act: -0.0002

Data Index: 314761 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1880. Min Act: -0.0003

Data Index: 299006 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1823. Min Act: -0.0002

Data Index: 363799 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1819. Min Act: -0.0002

Data Index: 324727 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1770. Min Act: -0.0002

Data Index: 379589 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1777. Min Act: -0.0002

Data Index: 50907 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1692. Min Act: -0.0002

Data Index: 307745 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1623. Min Act: -0.0002

Data Index: 1308413 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1635. Min Act: -0.0002

Data Index: 134431 (C4 (Web Text))

Max Activating Token Index: 447