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

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

Neuron 3756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2769. Min Range: -5.2769

Max Act: 5.2769. Min Act: -0.0000

Data Index: 520695 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 5.2769. Min Range: -5.2769

Max Act: 4.7936. Min Act: -0.0000

Data Index: 1210580 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 5.2769. Min Range: -5.2769

Max Act: 4.8015. Min Act: -0.0000

Data Index: 353903 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 5.2769. Min Range: -5.2769

Max Act: 4.0438. Min Act: -0.0000

Data Index: 1042744 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.7745. Min Act: -0.0000

Data Index: 883857 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.6415. Min Act: -0.0000

Data Index: 719319 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.4325. Min Act: -0.0000

Data Index: 1278605 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.2522. Min Act: -0.0000

Data Index: 1054452 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.5676. Min Act: -0.0000

Data Index: 891019 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.1746. Min Act: -0.0000

Data Index: 632248 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.1710. Min Act: -0.0000

Data Index: 473254 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 5.2769. Min Range: -5.2769

Max Act: 3.1409. Min Act: -0.0000

Data Index: 841599 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.9879. Min Act: -0.0000

Data Index: 487423 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.9777. Min Act: -0.0000

Data Index: 741437 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.9041. Min Act: -0.0000

Data Index: 1104165 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.6249. Min Act: -0.0000

Data Index: 2399 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.8679. Min Act: -0.0000

Data Index: 555425 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.8190. Min Act: -0.0000

Data Index: 216992 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.7717. Min Act: -0.0000

Data Index: 1125588 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 5.2769. Min Range: -5.2769

Max Act: 2.9169. Min Act: -0.0000

Data Index: 1342252 (C4 (Web Text))

Max Activating Token Index: 218