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

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

Neuron 1618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0000

Data Index: 579151 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0647. Min Act: -0.0001

Data Index: 936754 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0632. Min Act: -0.0001

Data Index: 856850 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0607. Min Act: -0.0001

Data Index: 439301 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0573. Min Act: -0.0001

Data Index: 563175 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0566. Min Act: -0.0001

Data Index: 585609 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0580. Min Act: -0.0001

Data Index: 738884 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0548. Min Act: -0.0001

Data Index: 318256 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0533. Min Act: -0.0001

Data Index: 507159 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0530. Min Act: -0.0001

Data Index: 113586 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1343338 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0485. Min Act: -0.0001

Data Index: 329982 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0498. Min Act: -0.0001

Data Index: 204458 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0500. Min Act: -0.0001

Data Index: 285640 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0453. Min Act: -0.0001

Data Index: 413226 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0503. Min Act: -0.0000

Data Index: 410163 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0508. Min Act: -0.0001

Data Index: 657814 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0486. Min Act: -0.0001

Data Index: 129568 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0487. Min Act: -0.0001

Data Index: 584176 (C4 (Web Text))

Max Activating Token Index: 54