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

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

Neuron 2315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.7092. Min Act: -0.0000

Data Index: 349662 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1221051 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1124666 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5650. Min Act: -0.0000

Data Index: 939301 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1000250 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1205447 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5482. Min Act: -0.0000

Data Index: 758312 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1029099 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1048102 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5701. Min Act: -0.0000

Data Index: 959648 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4906. Min Act: -0.0000

Data Index: 742219 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4925. Min Act: -0.0000

Data Index: 130816 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5573. Min Act: -0.0000

Data Index: 866142 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5312. Min Act: -0.0000

Data Index: 480637 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4409. Min Act: -0.0000

Data Index: 723509 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5254. Min Act: -0.0000

Data Index: 231169 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5364. Min Act: -0.0000

Data Index: 529930 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1021276 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4766. Min Act: -0.0000

Data Index: 756931 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4889. Min Act: -0.0000

Data Index: 893095 (C4 (Web Text))

Max Activating Token Index: 455