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

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

Neuron 2548 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.4568. Min Act: -0.0001

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.4716. Min Act: -0.0001

Data Index: 973645 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1025481 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3602. Min Act: -0.0001

Data Index: 120388 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3096. Min Act: -0.0001

Data Index: 505767 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3738. Min Act: -0.0001

Data Index: 1164943 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3178. Min Act: -0.0001

Data Index: 463614 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3197. Min Act: -0.0001

Data Index: 700809 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3392. Min Act: -0.0001

Data Index: 353612 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3586. Min Act: -0.0001

Data Index: 811447 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3533. Min Act: -0.0001

Data Index: 802040 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3159. Min Act: -0.0001

Data Index: 1140383 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2675. Min Act: -0.0001

Data Index: 1084550 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2919. Min Act: -0.0001

Data Index: 830117 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2800. Min Act: -0.0001

Data Index: 239986 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2472. Min Act: -0.0001

Data Index: 791173 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1922. Min Act: -0.0001

Data Index: 5512 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1947. Min Act: -0.0001

Data Index: 1107267 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1337. Min Act: -0.0001

Data Index: 210648 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2902. Min Act: -0.0001

Data Index: 324766 (C4 (Web Text))

Max Activating Token Index: 1009