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

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

Neuron 4142 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: 0.5842. Min Range: -0.5842

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1068796 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5586. Min Act: -0.0000

Data Index: 792124 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5487. Min Act: -0.0000

Data Index: 273723 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1082259 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4862. Min Act: -0.0000

Data Index: 812102 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1264376 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4355. Min Act: -0.0000

Data Index: 3547 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4279. Min Act: -0.0000

Data Index: 874971 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4269. Min Act: -0.0000

Data Index: 488233 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4566. Min Act: -0.0000

Data Index: 160832 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4258. Min Act: -0.0000

Data Index: 521718 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4071. Min Act: -0.0000

Data Index: 675857 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3950. Min Act: -0.0000

Data Index: 352007 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1048022 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1347405 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4142. Min Act: -0.0000

Data Index: 963258 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1230563 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3883. Min Act: -0.0000

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4282. Min Act: -0.0000

Data Index: 496016 (C4 (Web Text))

Max Activating Token Index: 824