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

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

Neuron 5834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1017. Min Range: -2.1017

Max Act: 2.1017. Min Act: -0.0000

Data Index: 279988 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.4485. Min Act: -0.0000

Data Index: 214619 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.3298. Min Act: -0.0000

Data Index: 447969 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1929. Min Act: -0.0000

Data Index: 137386 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2289. Min Act: -0.0000

Data Index: 275640 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1184283 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2072. Min Act: -0.0000

Data Index: 971635 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.3328. Min Act: -0.0000

Data Index: 610120 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1250928 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1487. Min Act: -0.0000

Data Index: 161386 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1073384 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.1208. Min Act: -0.0000

Data Index: 762406 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.2586. Min Act: -0.0000

Data Index: 1320795 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.0386. Min Act: -0.0000

Data Index: 513617 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.0483. Min Act: -0.0000

Data Index: 379851 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.0646. Min Act: -0.0000

Data Index: 813947 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.0413. Min Act: -0.0000

Data Index: 943625 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 2.1017. Min Range: -2.1017

Max Act: 0.9278. Min Act: -0.0000

Data Index: 391510 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 2.1017. Min Range: -2.1017

Max Act: 0.9921. Min Act: -0.0000

Data Index: 326183 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.0122. Min Act: -0.0000

Data Index: 772320 (C4 (Web Text))

Max Activating Token Index: 623