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

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

Neuron 1534 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: 1.9044. Min Range: -1.9044

Max Act: 1.9044. Min Act: -0.0002

Data Index: 419465 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5673. Min Act: -0.0002

Data Index: 664434 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4443. Min Act: -0.0002

Data Index: 1241550 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6323. Min Act: -0.0002

Data Index: 414524 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6991. Min Act: -0.0002

Data Index: 1188760 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5730. Min Act: -0.0002

Data Index: 585330 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5918. Min Act: -0.0002

Data Index: 1067868 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.7693. Min Act: -0.0002

Data Index: 551506 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6348. Min Act: -0.0002

Data Index: 1114603 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5706. Min Act: -0.0002

Data Index: 1033262 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5517. Min Act: -0.0002

Data Index: 571590 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4900. Min Act: -0.0002

Data Index: 172803 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4095. Min Act: -0.0002

Data Index: 1144853 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5371. Min Act: -0.0002

Data Index: 728502 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5180. Min Act: -0.0002

Data Index: 1134225 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5103. Min Act: -0.0002

Data Index: 85802 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4139. Min Act: -0.0002

Data Index: 895710 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5897. Min Act: -0.0002

Data Index: 685802 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5961. Min Act: -0.0002

Data Index: 1246627 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6397. Min Act: -0.0002

Data Index: 852517 (C4 (Web Text))

Max Activating Token Index: 724