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

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

Neuron 87 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.3081. Min Act: -0.0002

Data Index: 835190 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.1713. Min Act: -0.0002

Data Index: 643042 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.2299. Min Act: -0.0002

Data Index: 959922 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0963. Min Act: -0.0002

Data Index: 873516 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.1425. Min Act: -0.0002

Data Index: 475223 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.2505. Min Act: -0.0002

Data Index: 155241 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.1768. Min Act: -0.0002

Data Index: 803409 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.2749. Min Act: -0.0002

Data Index: 985539 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.3370. Min Act: -0.0002

Data Index: 617116 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0760. Min Act: -0.0002

Data Index: 647216 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.1306. Min Act: -0.0002

Data Index: 122607 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.3370. Min Range: -2.3370

Max Act: 1.9698. Min Act: -0.0002

Data Index: 990956 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0309. Min Act: -0.0002

Data Index: 789174 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0699. Min Act: -0.0002

Data Index: 1001984 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 2.3370. Min Range: -2.3370

Max Act: 1.9450. Min Act: -0.0002

Data Index: 318645 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 2.3370. Min Range: -2.3370

Max Act: 1.9485. Min Act: -0.0002

Data Index: 1244595 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 2.3370. Min Range: -2.3370

Max Act: 1.9451. Min Act: -0.0002

Data Index: 387681 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0947. Min Act: -0.0002

Data Index: 593742 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.1486. Min Act: -0.0002

Data Index: 793579 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 2.3370. Min Range: -2.3370

Max Act: 2.0966. Min Act: -0.0002

Data Index: 54831 (C4 (Web Text))

Max Activating Token Index: 211