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

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

Neuron 474 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3414. Min Range: -2.3414

Max Act: 2.0489. Min Act: -0.0000

Data Index: 118821 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.3414. Min Range: -2.3414

Max Act: 2.3414. Min Act: -0.0000

Data Index: 1348752 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.9547. Min Act: -0.0000

Data Index: 203721 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1406939 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.4899. Min Act: -0.0000

Data Index: 324440 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.5448. Min Act: -0.0000

Data Index: 138523 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.3242. Min Act: -0.0000

Data Index: 286181 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1085806 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1551419 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.1922. Min Act: -0.0000

Data Index: 408214 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.1389. Min Act: -0.0000

Data Index: 477494 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1230799 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.1829. Min Act: -0.0000

Data Index: 644213 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.0853. Min Act: -0.0000

Data Index: 581618 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1267575 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 2.3414. Min Range: -2.3414

Max Act: 0.9877. Min Act: -0.0000

Data Index: 211198 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 2.3414. Min Range: -2.3414

Max Act: 0.9209. Min Act: -0.0000

Data Index: 563505 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.0090. Min Act: -0.0000

Data Index: 961997 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 2.3414. Min Range: -2.3414

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1158866 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 2.3414. Min Range: -2.3414

Max Act: 0.9989. Min Act: -0.0000

Data Index: 233412 (C4 (Web Text))

Max Activating Token Index: 466