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

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

Neuron 2839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2929. Min Act: -0.0000

Data Index: 592664 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2916. Min Act: -0.0000

Data Index: 53209 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2650. Min Act: -0.0000

Data Index: 785415 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2711. Min Act: -0.0000

Data Index: 52609 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2703. Min Act: -0.0000

Data Index: 820962 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2622. Min Act: -0.0000

Data Index: 960553 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2608. Min Act: -0.0000

Data Index: 57088 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2589. Min Act: 0.0000

Data Index: 372377 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2365. Min Act: -0.0000

Data Index: 725028 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2451. Min Act: -0.0000

Data Index: 233391 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2313. Min Act: -0.0000

Data Index: 396095 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1251875 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1199978 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2282. Min Act: -0.0000

Data Index: 790774 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2371. Min Act: -0.0000

Data Index: 610559 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1099804 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2435. Min Act: -0.0000

Data Index: 316588 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2202. Min Act: -0.0000

Data Index: 428060 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1022299 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1004591 (C4 (Web Text))

Max Activating Token Index: 500