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

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

Neuron 2865 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.2089. Min Act: -0.0000

Data Index: 592504 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1481. Min Act: -0.0000

Data Index: 677575 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1442. Min Act: -0.0000

Data Index: 884129 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1387. Min Act: -0.0000

Data Index: 853430 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0908. Min Act: -0.0000

Data Index: 222942 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1316839 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0428. Min Act: -0.0000

Data Index: 319745 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0001. Min Act: -0.0000

Data Index: 693381 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0008. Min Act: -0.0000

Data Index: 857873 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9543. Min Act: -0.0000

Data Index: 20292 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0434. Min Act: -0.0000

Data Index: 957742 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9233. Min Act: -0.0000

Data Index: 995956 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1324535 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9767. Min Act: -0.0000

Data Index: 649302 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9134. Min Act: -0.0000

Data Index: 173940 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9832. Min Act: -0.0000

Data Index: 31909 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9095. Min Act: -0.0000

Data Index: 792697 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9054. Min Act: -0.0000

Data Index: 981841 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.8322. Min Act: -0.0000

Data Index: 164207 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.8622. Min Act: -0.0000

Data Index: 915949 (C4 (Web Text))

Max Activating Token Index: 811