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

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

Neuron 21 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: 4.6234. Min Range: -4.6234

Max Act: 4.5412. Min Act: -0.0000

Data Index: 917440 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.4998. Min Act: -0.0000

Data Index: 881426 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.6234. Min Act: -0.0000

Data Index: 686912 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.4326. Min Act: -0.0000

Data Index: 1098056 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.1815. Min Act: -0.0000

Data Index: 493300 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.5026. Min Act: -0.0000

Data Index: 199824 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.4064. Min Act: -0.0000

Data Index: 587877 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.1499. Min Act: -0.0000

Data Index: 466010 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.7764. Min Act: -0.0000

Data Index: 76174 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.8936. Min Act: -0.0000

Data Index: 437718 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.0577. Min Act: -0.0000

Data Index: 407331 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.8793. Min Act: -0.0000

Data Index: 508651 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.1776. Min Act: -0.0000

Data Index: 684979 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.0211. Min Act: -0.0000

Data Index: 1040297 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.1870. Min Act: -0.0000

Data Index: 479278 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.9555. Min Act: -0.0000

Data Index: 583728 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.6447. Min Act: -0.0000

Data Index: 187884 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 4.6234. Min Range: -4.6234

Max Act: 3.8089. Min Act: -0.0000

Data Index: 1318689 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.0906. Min Act: -0.0000

Data Index: 395758 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 4.6234. Min Range: -4.6234

Max Act: 4.0364. Min Act: -0.0000

Data Index: 389971 (C4 (Web Text))

Max Activating Token Index: 29