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

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

Neuron 4131 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1209581 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1227392 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0694. Min Act: -0.0001

Data Index: 207702 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1247357 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0656. Min Act: -0.0001

Data Index: 714607 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0648. Min Act: -0.0001

Data Index: 212899 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0659. Min Act: -0.0001

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0621. Min Act: -0.0001

Data Index: 659165 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0573. Min Act: -0.0001

Data Index: 432690 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0608. Min Act: -0.0001

Data Index: 347280 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0585. Min Act: -0.0001

Data Index: 661823 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1052247 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0600. Min Act: -0.0001

Data Index: 992429 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1176216 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0599. Min Act: -0.0001

Data Index: 814264 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0597. Min Act: -0.0001

Data Index: 277454 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1294311 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0616. Min Act: -0.0001

Data Index: 40592 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0589. Min Act: -0.0001

Data Index: 265750 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0602. Min Act: -0.0001

Data Index: 795639 (C4 (Web Text))

Max Activating Token Index: 606