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

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

Neuron 4130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.2594. Min Act: -0.0000

Data Index: 430248 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.3671. Min Act: -0.0000

Data Index: 300958 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.3263. Min Act: -0.0000

Data Index: 408366 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.1991. Min Act: -0.0000

Data Index: 364945 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.2801. Min Act: -0.0000

Data Index: 80689 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.2741. Min Act: -0.0000

Data Index: 998289 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.1356. Min Act: -0.0000

Data Index: 122385 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.1936. Min Act: -0.0000

Data Index: 877120 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.1772. Min Act: -0.0000

Data Index: 1315714 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0972. Min Act: -0.0000

Data Index: 1330054 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1044118 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0674. Min Act: -0.0000

Data Index: 100689 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0571. Min Act: -0.0000

Data Index: 559508 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0040. Min Act: -0.0000

Data Index: 177184 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0930. Min Act: -0.0000

Data Index: 251703 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0980. Min Act: -0.0000

Data Index: 766256 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.9650. Min Act: -0.0000

Data Index: 1061081 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0668. Min Act: -0.0000

Data Index: 348780 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8033. Min Act: -0.0000

Data Index: 633566 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8994. Min Act: -0.0000

Data Index: 548661 (C4 (Web Text))

Max Activating Token Index: 134