Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2626 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0001

Data Index: 477481 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8401. Min Act: -0.0002

Data Index: 1217998 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8543. Min Act: -0.0001

Data Index: 176212 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7235. Min Act: -0.0001

Data Index: 496518 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7388. Min Act: -0.0001

Data Index: 787992 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7175. Min Act: -0.0001

Data Index: 1269647 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1177335 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6889. Min Act: -0.0002

Data Index: 806600 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7286. Min Act: -0.0001

Data Index: 671218 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6642. Min Act: -0.0001

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1230630 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1348827 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6673. Min Act: -0.0002

Data Index: 1330712 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6627. Min Act: -0.0002

Data Index: 276028 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7054. Min Act: -0.0001

Data Index: 635880 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6719. Min Act: -0.0001

Data Index: 473180 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6746. Min Act: -0.0002

Data Index: 232854 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6490. Min Act: -0.0001

Data Index: 875431 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5682. Min Act: -0.0001

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6469. Min Act: -0.0001

Data Index: 137899 (C4 (Web Text))

Max Activating Token Index: 636