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

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

Neuron 4903 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8530. Min Act: -0.0001

Data Index: 1060624 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5096. Min Act: -0.0001

Data Index: 1003733 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3782. Min Act: -0.0001

Data Index: 882608 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3493. Min Act: -0.0001

Data Index: 868208 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.4649. Min Act: -0.0001

Data Index: 396225 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3491. Min Act: -0.0001

Data Index: 241011 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.4876. Min Act: -0.0001

Data Index: 1156983 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3429. Min Act: -0.0001

Data Index: 804712 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2379. Min Act: -0.0001

Data Index: 489633 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.1870. Min Act: -0.0001

Data Index: 534559 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3298. Min Act: -0.0001

Data Index: 1307376 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2620. Min Act: -0.0001

Data Index: 992990 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2524. Min Act: -0.0001

Data Index: 938227 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2934. Min Act: -0.0001

Data Index: 123112 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.4265. Min Act: -0.0001

Data Index: 527963 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.3037. Min Act: -0.0001

Data Index: 450975 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2270. Min Act: -0.0001

Data Index: 1146961 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.1463. Min Act: -0.0001

Data Index: 757880 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.4182. Min Act: -0.0001

Data Index: 1267184 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.2147. Min Act: -0.0001

Data Index: 680368 (C4 (Web Text))

Max Activating Token Index: 507