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

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

Neuron 985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0743. Min Range: -2.0743

Max Act: 2.0743. Min Act: -0.0000

Data Index: 210457 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.9636. Min Act: -0.0000

Data Index: 915924 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.7656. Min Act: -0.0000

Data Index: 606461 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.7481. Min Act: -0.0000

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.6863. Min Act: -0.0000

Data Index: 634878 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.6180. Min Act: -0.0000

Data Index: 802248 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.6937. Min Act: -0.0000

Data Index: 88350 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.4009. Min Act: -0.0000

Data Index: 848158 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.4707. Min Act: -0.0000

Data Index: 932127 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.3343. Min Act: -0.0000

Data Index: 712731 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.2360. Min Act: -0.0000

Data Index: 476641 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.3095. Min Act: -0.0000

Data Index: 754415 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1278116 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.2386. Min Act: -0.0000

Data Index: 319954 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.1561. Min Act: -0.0000

Data Index: 748354 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.1365. Min Act: -0.0000

Data Index: 650805 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.2620. Min Act: -0.0000

Data Index: 711988 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.1006. Min Act: -0.0000

Data Index: 412364 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.2100. Min Act: -0.0000

Data Index: 914420 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.0743. Min Range: -2.0743

Max Act: 1.1429. Min Act: -0.0000

Data Index: 961731 (C4 (Web Text))

Max Activating Token Index: 865