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

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

Neuron 3347 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1409. Min Range: -2.1409

Max Act: 2.1409. Min Act: -0.0000

Data Index: 340870 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.5230. Min Act: -0.0000

Data Index: 109719 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.4953. Min Act: -0.0000

Data Index: 900089 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.4060. Min Act: -0.0000

Data Index: 668057 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1153146 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1058750 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.3749. Min Act: -0.0000

Data Index: 549103 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1883. Min Act: -0.0000

Data Index: 859197 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1237102 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1675. Min Act: -0.0000

Data Index: 823219 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1949. Min Act: -0.0000

Data Index: 212358 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.2639. Min Act: -0.0000

Data Index: 982232 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.0840. Min Act: -0.0000

Data Index: 7878 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1323945 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1513. Min Act: -0.0000

Data Index: 843898 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1609. Min Act: -0.0000

Data Index: 444758 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1121636 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1001. Min Act: -0.0000

Data Index: 770893 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1062. Min Act: -0.0000

Data Index: 241167 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.1409. Min Range: -2.1409

Max Act: 1.1064. Min Act: -0.0000

Data Index: 779228 (C4 (Web Text))

Max Activating Token Index: 1010