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

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

Neuron 3977 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: 0.2232. Min Range: -0.2232

Max Act: 0.2232. Min Act: -0.0002

Data Index: 652740 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2046. Min Act: -0.0002

Data Index: 3282 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1892. Min Act: -0.0002

Data Index: 642228 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1747. Min Act: -0.0002

Data Index: 776593 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1583. Min Act: -0.0002

Data Index: 1249662 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1673. Min Act: -0.0002

Data Index: 1178157 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1676. Min Act: -0.0002

Data Index: 944659 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1351821 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1630. Min Act: -0.0002

Data Index: 512947 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1666. Min Act: -0.0002

Data Index: 616204 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1639. Min Act: -0.0002

Data Index: 528164 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1597. Min Act: -0.0002

Data Index: 1210604 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1705. Min Act: -0.0002

Data Index: 1162877 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1556. Min Act: -0.0002

Data Index: 654459 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1581. Min Act: -0.0002

Data Index: 405586 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1585. Min Act: -0.0002

Data Index: 573704 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1552. Min Act: -0.0002

Data Index: 546394 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1568. Min Act: -0.0002

Data Index: 518645 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1521. Min Act: -0.0002

Data Index: 1270432 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1421. Min Act: -0.0002

Data Index: 410216 (C4 (Web Text))

Max Activating Token Index: 311