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

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

Neuron 4175 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: 0.0494. Min Range: -0.0494

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1254032 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0477. Min Act: -0.0002

Data Index: 856689 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0002

Data Index: 265930 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0472. Min Act: -0.0002

Data Index: 901051 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0447. Min Act: -0.0002

Data Index: 680055 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0436. Min Act: -0.0002

Data Index: 809289 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0431. Min Act: -0.0002

Data Index: 105458 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0408. Min Act: -0.0002

Data Index: 308612 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0392. Min Act: -0.0002

Data Index: 101877 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0404. Min Act: -0.0002

Data Index: 357643 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1131870 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1258272 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0401. Min Act: -0.0002

Data Index: 922380 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1195422 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0387. Min Act: -0.0002

Data Index: 84783 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0400. Min Act: -0.0002

Data Index: 65307 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0400. Min Act: -0.0002

Data Index: 913809 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1044177 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0385. Min Act: -0.0002

Data Index: 962262 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0382. Min Act: -0.0002

Data Index: 102874 (C4 (Web Text))

Max Activating Token Index: 484