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

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

Neuron 4281 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1087841 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6473. Min Act: -0.0000

Data Index: 164883 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6362. Min Act: -0.0000

Data Index: 249942 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6070. Min Act: -0.0000

Data Index: 607813 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5911. Min Act: -0.0000

Data Index: 345349 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5879. Min Act: -0.0000

Data Index: 170399 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1185375 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5700. Min Act: -0.0000

Data Index: 153597 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5634. Min Act: -0.0000

Data Index: 736033 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1090621 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5690. Min Act: -0.0000

Data Index: 316242 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5458. Min Act: -0.0000

Data Index: 436220 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5396. Min Act: -0.0000

Data Index: 415485 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5150. Min Act: -0.0000

Data Index: 19784 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5463. Min Act: -0.0000

Data Index: 792253 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5251. Min Act: -0.0000

Data Index: 921846 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5172. Min Act: -0.0000

Data Index: 37884 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4873. Min Act: -0.0000

Data Index: 653612 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5173. Min Act: -0.0000

Data Index: 300770 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1094845 (C4 (Web Text))

Max Activating Token Index: 664