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

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

Neuron 3801 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1171619 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4943. Min Act: -0.0000

Data Index: 896901 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5701. Min Act: -0.0000

Data Index: 689663 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5453. Min Act: -0.0000

Data Index: 778490 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5104. Min Act: -0.0000

Data Index: 323281 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4496. Min Act: -0.0000

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4676. Min Act: -0.0000

Data Index: 736548 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4594. Min Act: -0.0000

Data Index: 311422 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1003568 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4703. Min Act: -0.0000

Data Index: 349398 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4354. Min Act: -0.0000

Data Index: 519879 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1193345 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4190. Min Act: -0.0000

Data Index: 564063 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4693. Min Act: -0.0000

Data Index: 374390 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4108. Min Act: -0.0000

Data Index: 644176 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.3835. Min Act: -0.0000

Data Index: 10070 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1062133 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.3801. Min Act: -0.0000

Data Index: 582567 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.3680. Min Act: -0.0000

Data Index: 838801 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1162226 (C4 (Web Text))

Max Activating Token Index: 1004