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

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

Neuron 1022 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: 0.8351. Min Range: -0.8351

Max Act: 0.8351. Min Act: 0.0000

Data Index: 1330511 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7440. Min Act: 0.0001

Data Index: 502028 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7563. Min Act: 0.0000

Data Index: 379063 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1291537 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1119238 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7652. Min Act: -0.0000

Data Index: 877014 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.7560. Min Act: -0.0000

Data Index: 982506 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6979. Min Act: -0.0000

Data Index: 609927 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6912. Min Act: -0.0000

Data Index: 632307 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6793. Min Act: -0.0000

Data Index: 567049 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6561. Min Act: -0.0000

Data Index: 358559 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6515. Min Act: -0.0000

Data Index: 448853 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1090967 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1226886 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6058. Min Act: -0.0000

Data Index: 194562 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1070683 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1040307 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1190995 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.5876. Min Act: -0.0000

Data Index: 886943 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.8351. Min Range: -0.8351

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1152117 (C4 (Web Text))

Max Activating Token Index: 823