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

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

Neuron 11 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6412. Min Range: -2.6412

Max Act: 2.6412. Min Act: -0.0000

Data Index: 606732 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.9231. Min Act: -0.0001

Data Index: 1119436 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.7087. Min Act: -0.0000

Data Index: 560957 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.6141. Min Act: -0.0000

Data Index: 997162 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.5153. Min Act: -0.0000

Data Index: 273199 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.5976. Min Act: -0.0001

Data Index: 37377 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4316. Min Act: -0.0000

Data Index: 178233 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1139453 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.5251. Min Act: -0.0001

Data Index: 372786 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4587. Min Act: -0.0001

Data Index: 280866 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4833. Min Act: -0.0000

Data Index: 770144 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1185209 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4310. Min Act: -0.0000

Data Index: 343810 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4196. Min Act: -0.0001

Data Index: 321065 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.3873. Min Act: -0.0000

Data Index: 364429 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.3747. Min Act: -0.0000

Data Index: 992289 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4087. Min Act: -0.0001

Data Index: 524355 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1076884 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.3484. Min Act: -0.0001

Data Index: 514669 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 2.6412. Min Range: -2.6412

Max Act: 1.3743. Min Act: -0.0000

Data Index: 371461 (C4 (Web Text))

Max Activating Token Index: 117