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

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

Neuron 4273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3456. Min Act: -0.0000

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0000

Data Index: 979409 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3194. Min Act: -0.0000

Data Index: 420757 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3048. Min Act: -0.0000

Data Index: 905557 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3110. Min Act: -0.0001

Data Index: 662041 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3106. Min Act: -0.0000

Data Index: 501551 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2902. Min Act: -0.0000

Data Index: 173594 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2513. Min Act: -0.0001

Data Index: 1279253 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1127422 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2500. Min Act: -0.0000

Data Index: 432768 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1190519 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2417. Min Act: -0.0001

Data Index: 830270 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1859. Min Act: -0.0000

Data Index: 322220 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1910. Min Act: -0.0000

Data Index: 542263 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1809. Min Act: -0.0000

Data Index: 905489 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1976. Min Act: -0.0000

Data Index: 619335 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1839. Min Act: -0.0000

Data Index: 763062 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1131651 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1727. Min Act: -0.0000

Data Index: 384135 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1268704 (C4 (Web Text))

Max Activating Token Index: 700