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

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

Neuron 3072 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.1031. Min Act: -0.0000

Data Index: 490945 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9855. Min Act: -0.0000

Data Index: 699602 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8328. Min Act: -0.0000

Data Index: 575972 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.5227. Min Act: -0.0000

Data Index: 127275 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.4503. Min Act: -0.0000

Data Index: 380978 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.4456. Min Act: -0.0000

Data Index: 725469 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.4214. Min Act: -0.0000

Data Index: 650872 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3800. Min Act: -0.0000

Data Index: 560605 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3962. Min Act: -0.0000

Data Index: 810590 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1289701 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.4060. Min Act: -0.0000

Data Index: 42636 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3669. Min Act: 0.0000

Data Index: 1212009 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1291380 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3648. Min Act: -0.0000

Data Index: 708744 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3209. Min Act: -0.0000

Data Index: 549982 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3775. Min Act: -0.0000

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3384. Min Act: -0.0000

Data Index: 985848 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1160234 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3561. Min Act: -0.0000

Data Index: 573166 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.3067. Min Act: -0.0000

Data Index: 478665 (C4 (Web Text))

Max Activating Token Index: 379