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

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

Neuron 4642 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.4963. Min Act: -0.0001

Data Index: 377263 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.4591. Min Act: -0.0000

Data Index: 495153 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.2639. Min Act: -0.0000

Data Index: 1029979 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.0929. Min Act: -0.0001

Data Index: 434950 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.0918. Min Act: -0.0000

Data Index: 387937 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.9574. Min Act: -0.0000

Data Index: 627917 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.9220. Min Act: -0.0000

Data Index: 806651 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.0498. Min Act: -0.0001

Data Index: 370754 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8938. Min Act: -0.0000

Data Index: 919867 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.4963. Min Range: -2.4963

Max Act: 2.1110. Min Act: -0.0000

Data Index: 1258071 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8105. Min Act: -0.0000

Data Index: 924068 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.7897. Min Act: -0.0001

Data Index: 770864 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8726. Min Act: -0.0000

Data Index: 29125 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8692. Min Act: -0.0000

Data Index: 843106 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8680. Min Act: -0.0000

Data Index: 732879 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8652. Min Act: -0.0001

Data Index: 1297060 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8590. Min Act: -0.0000

Data Index: 539253 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1009014 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.7808. Min Act: -0.0001

Data Index: 400296 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.4963. Min Range: -2.4963

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1031467 (C4 (Web Text))

Max Activating Token Index: 291