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

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

Neuron 1628 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3635. Min Act: -0.0000

Data Index: 459569 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3041. Min Act: -0.0000

Data Index: 68307 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2916. Min Act: -0.0000

Data Index: 891184 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2852. Min Act: 0.0001

Data Index: 1238468 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2869. Min Act: -0.0000

Data Index: 423126 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2739. Min Act: 0.0001

Data Index: 950302 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2786. Min Act: 0.0000

Data Index: 410873 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1255820 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2865. Min Act: -0.0000

Data Index: 574924 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2654. Min Act: -0.0000

Data Index: 579287 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2682. Min Act: -0.0000

Data Index: 922790 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2563. Min Act: -0.0000

Data Index: 444888 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2568. Min Act: -0.0000

Data Index: 20821 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1212896 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2427. Min Act: -0.0000

Data Index: 440555 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2405. Min Act: 0.0002

Data Index: 1066730 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2573. Min Act: -0.0000

Data Index: 325336 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2428. Min Act: -0.0000

Data Index: 26051 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2417. Min Act: 0.0001

Data Index: 643497 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1328439 (C4 (Web Text))

Max Activating Token Index: 460