Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.5008. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.5106. Min Act: -0.0000

Data Index: 761020 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.2387. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.1665. Min Act: -0.0000

Data Index: 9380 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1187378 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.9553. Min Act: -0.0000

Data Index: 139911 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.9050. Min Act: -0.0000

Data Index: 924495 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 2.5106. Min Range: -2.5106

Max Act: 2.0536. Min Act: -0.0000

Data Index: 912138 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8849. Min Act: -0.0000

Data Index: 328509 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8867. Min Act: -0.0000

Data Index: 51134 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1134552 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8490. Min Act: -0.0000

Data Index: 956463 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.9498. Min Act: -0.0000

Data Index: 440757 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8112. Min Act: -0.0000

Data Index: 476931 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.7212. Min Act: -0.0000

Data Index: 65284 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1120034 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8069. Min Act: -0.0000

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.8004. Min Act: -0.0000

Data Index: 55999 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.6950. Min Act: -0.0000

Data Index: 161508 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 2.5106. Min Range: -2.5106

Max Act: 1.7792. Min Act: -0.0000

Data Index: 193746 (C4 (Web Text))

Max Activating Token Index: 546