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

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

Neuron 1092 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8047. Min Act: -0.0000

Data Index: 482 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1160263 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8250. Min Act: -0.0000

Data Index: 290657 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1349405 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8082. Min Act: -0.0000

Data Index: 486401 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7993. Min Act: -0.0000

Data Index: 838713 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1292575 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1185303 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7351. Min Act: -0.0000

Data Index: 35402 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7346. Min Act: -0.0000

Data Index: 779382 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7201. Min Act: -0.0000

Data Index: 743539 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6906. Min Act: -0.0000

Data Index: 834149 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6561. Min Act: -0.0000

Data Index: 782608 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6929. Min Act: -0.0000

Data Index: 97059 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6696. Min Act: -0.0000

Data Index: 480641 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6886. Min Act: -0.0000

Data Index: 815586 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6806. Min Act: -0.0000

Data Index: 840510 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6566. Min Act: -0.0000

Data Index: 643320 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6352. Min Act: -0.0000

Data Index: 409976 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1213364 (C4 (Web Text))

Max Activating Token Index: 488