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

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

Neuron 2752 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.9507. Min Act: -0.0002

Data Index: 501173 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.7185. Min Act: -0.0002

Data Index: 1290417 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.6509. Min Act: -0.0001

Data Index: 371248 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.8331. Min Act: -0.0001

Data Index: 1205642 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.6317. Min Act: -0.0001

Data Index: 1147509 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.6193. Min Act: -0.0002

Data Index: 952075 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.6487. Min Act: -0.0002

Data Index: 1115599 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5583. Min Act: -0.0001

Data Index: 219062 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5840. Min Act: -0.0001

Data Index: 302097 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5326. Min Act: -0.0002

Data Index: 148961 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4938. Min Act: -0.0002

Data Index: 392450 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5077. Min Act: -0.0001

Data Index: 1030015 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4927. Min Act: -0.0001

Data Index: 25827 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4864. Min Act: -0.0002

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5376. Min Act: -0.0002

Data Index: 333080 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4024. Min Act: -0.0001

Data Index: 1015832 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.5257. Min Act: -0.0002

Data Index: 939732 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4863. Min Act: -0.0001

Data Index: 1020858 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.4253. Min Act: -0.0002

Data Index: 780412 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.9507. Min Range: -1.9507

Max Act: 1.3974. Min Act: -0.0001

Data Index: 648409 (C4 (Web Text))

Max Activating Token Index: 603