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

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

Neuron 2274 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5462. Min Act: -0.0000

Data Index: 797298 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4967. Min Act: -0.0000

Data Index: 13293 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1121008 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1270339 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4895. Min Act: -0.0000

Data Index: 318758 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4651. Min Act: -0.0000

Data Index: 402235 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4633. Min Act: -0.0000

Data Index: 880931 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4393. Min Act: -0.0000

Data Index: 940131 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4372. Min Act: -0.0000

Data Index: 72800 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1119808 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4168. Min Act: -0.0000

Data Index: 289145 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4118. Min Act: -0.0000

Data Index: 983698 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4156. Min Act: -0.0000

Data Index: 933105 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4247. Min Act: -0.0000

Data Index: 333826 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4430. Min Act: -0.0000

Data Index: 702326 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4058. Min Act: -0.0000

Data Index: 295074 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3969. Min Act: -0.0000

Data Index: 954058 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3917. Min Act: -0.0001

Data Index: 1101282 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4021. Min Act: -0.0000

Data Index: 921438 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3579. Min Act: -0.0000

Data Index: 59465 (C4 (Web Text))

Max Activating Token Index: 844