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

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

Neuron 4724 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0002

Data Index: 500414 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0496. Min Act: -0.0002

Data Index: 74187 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0458. Min Act: -0.0003

Data Index: 317783 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0442. Min Act: -0.0003

Data Index: 995584 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0450. Min Act: -0.0003

Data Index: 397497 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0447. Min Act: -0.0003

Data Index: 560659 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0438. Min Act: -0.0003

Data Index: 776106 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0470. Min Act: -0.0003

Data Index: 755710 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0442. Min Act: -0.0003

Data Index: 790226 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0432. Min Act: -0.0003

Data Index: 709780 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0435. Min Act: -0.0003

Data Index: 91433 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0424. Min Act: -0.0003

Data Index: 309541 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0425. Min Act: -0.0003

Data Index: 529221 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0441. Min Act: -0.0003

Data Index: 700532 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0424. Min Act: -0.0003

Data Index: 377810 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0414. Min Act: -0.0002

Data Index: 423035 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0428. Min Act: -0.0003

Data Index: 742447 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0413. Min Act: -0.0003

Data Index: 332599 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1088590 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0416. Min Act: -0.0003

Data Index: 270554 (C4 (Web Text))

Max Activating Token Index: 56