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

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

Neuron 3364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1339. Min Range: -4.1339

Max Act: 4.1339. Min Act: -0.0000

Data Index: 1132946 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 4.1339. Min Range: -4.1339

Max Act: 3.1634. Min Act: -0.0000

Data Index: 175675 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.9722. Min Act: -0.0000

Data Index: 306253 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.8956. Min Act: -0.0000

Data Index: 684721 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 4.1339. Min Range: -4.1339

Max Act: 3.0358. Min Act: -0.0000

Data Index: 954581 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4451. Min Act: -0.0000

Data Index: 1267741 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.7980. Min Act: -0.0000

Data Index: 261279 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.6296. Min Act: -0.0000

Data Index: 718378 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4359. Min Act: -0.0000

Data Index: 577148 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4112. Min Act: -0.0000

Data Index: 169831 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4952. Min Act: -0.0000

Data Index: 1138947 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.5222. Min Act: -0.0000

Data Index: 180958 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.1337. Min Act: -0.0000

Data Index: 736655 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.3644. Min Act: -0.0000

Data Index: 764353 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1164525 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.4490. Min Act: -0.0000

Data Index: 910116 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.3080. Min Act: -0.0000

Data Index: 184046 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.2868. Min Act: -0.0000

Data Index: 486139 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.2926. Min Act: -0.0000

Data Index: 500128 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 4.1339. Min Range: -4.1339

Max Act: 2.2826. Min Act: -0.0000

Data Index: 119838 (C4 (Web Text))

Max Activating Token Index: 146