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

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

Neuron 3726 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8385. Min Act: -0.0001

Data Index: 210579 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6394. Min Act: -0.0001

Data Index: 901858 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6832. Min Act: -0.0001

Data Index: 1094551 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6368. Min Act: -0.0001

Data Index: 1114592 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4557. Min Act: -0.0001

Data Index: 1245997 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5934. Min Act: -0.0001

Data Index: 1241632 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5088. Min Act: -0.0001

Data Index: 222404 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5085. Min Act: -0.0001

Data Index: 1030235 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4313. Min Act: -0.0001

Data Index: 1050777 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4577. Min Act: -0.0001

Data Index: 1189790 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4239. Min Act: -0.0001

Data Index: 971870 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5068. Min Act: -0.0001

Data Index: 433405 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4952. Min Act: -0.0001

Data Index: 277495 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4810. Min Act: -0.0001

Data Index: 617145 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.3901. Min Act: -0.0001

Data Index: 1205678 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4091. Min Act: -0.0001

Data Index: 363009 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4187. Min Act: -0.0001

Data Index: 761557 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4243. Min Act: -0.0001

Data Index: 405909 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.3742. Min Act: -0.0001

Data Index: 381640 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4383. Min Act: -0.0001

Data Index: 906149 (C4 (Web Text))

Max Activating Token Index: 952