Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1124 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1062260 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.5930. Min Act: -0.0000

Data Index: 175457 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.5345. Min Act: -0.0000

Data Index: 496606 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.5179. Min Act: -0.0000

Data Index: 205193 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4940. Min Act: -0.0000

Data Index: 815530 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.5088. Min Act: -0.0000

Data Index: 271504 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4977. Min Act: -0.0000

Data Index: 295869 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1333440 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1202759 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4838. Min Act: -0.0000

Data Index: 265101 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4553. Min Act: -0.0000

Data Index: 913467 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4464. Min Act: -0.0000

Data Index: 818329 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4262. Min Act: -0.0000

Data Index: 570748 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4057. Min Act: -0.0000

Data Index: 327576 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4224. Min Act: -0.0000

Data Index: 662790 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4423. Min Act: 0.0000

Data Index: 267348 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.4227. Min Act: -0.0000

Data Index: 633770 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1174055 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.3931. Min Act: -0.0000

Data Index: 799800 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.6571. Min Range: -0.6571

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1028764 (C4 (Web Text))

Max Activating Token Index: 425