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

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

Neuron 1584 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.3364. Min Act: -0.0002

Data Index: 338758 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1977. Min Act: -0.0002

Data Index: 655392 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1026. Min Act: -0.0002

Data Index: 1323749 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7878. Min Act: -0.0002

Data Index: 666575 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6691. Min Act: -0.0002

Data Index: 1114171 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6342. Min Act: -0.0002

Data Index: 775349 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6228. Min Act: -0.0002

Data Index: 953708 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6467. Min Act: -0.0002

Data Index: 40295 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6245. Min Act: -0.0002

Data Index: 374398 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6047. Min Act: -0.0002

Data Index: 15420 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6050. Min Act: -0.0002

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6404. Min Act: -0.0002

Data Index: 576032 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6147. Min Act: -0.0002

Data Index: 1299203 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6140. Min Act: -0.0002

Data Index: 899659 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.5505. Min Act: -0.0002

Data Index: 2312 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6061. Min Act: -0.0002

Data Index: 518238 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6228. Min Act: -0.0002

Data Index: 49288 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.5705. Min Act: -0.0002

Data Index: 491125 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.5752. Min Act: -0.0002

Data Index: 611384 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.6145. Min Act: -0.0002

Data Index: 274829 (C4 (Web Text))

Max Activating Token Index: 661