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

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

Neuron 1539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.8132. Min Act: -0.0001

Data Index: 1341364 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5990. Min Act: -0.0001

Data Index: 813916 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6790. Min Act: -0.0001

Data Index: 1321103 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.7771. Min Act: -0.0001

Data Index: 773704 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6914. Min Act: -0.0001

Data Index: 67013 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5324. Min Act: -0.0001

Data Index: 1135338 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5564. Min Act: -0.0001

Data Index: 556110 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4136. Min Act: -0.0001

Data Index: 96405 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5707. Min Act: -0.0001

Data Index: 1346453 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4863. Min Act: -0.0001

Data Index: 725312 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5232. Min Act: -0.0001

Data Index: 1218817 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5585. Min Act: -0.0001

Data Index: 1221496 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5501. Min Act: -0.0001

Data Index: 230883 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5903. Min Act: -0.0001

Data Index: 425255 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4542. Min Act: -0.0001

Data Index: 401374 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4706. Min Act: -0.0001

Data Index: 976111 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4359. Min Act: -0.0001

Data Index: 1069567 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5119. Min Act: -0.0001

Data Index: 1321484 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.4138. Min Act: -0.0001

Data Index: 1136262 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5315. Min Act: -0.0001

Data Index: 962748 (C4 (Web Text))

Max Activating Token Index: 341