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

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

Neuron 1976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.7082. Min Act: -0.0000

Data Index: 328813 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.7234. Min Act: -0.0000

Data Index: 559558 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.4422. Min Act: -0.0000

Data Index: 1194169 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.4808. Min Act: -0.0000

Data Index: 707339 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1237292 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.4542. Min Act: -0.0000

Data Index: 918947 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.1012. Min Act: -0.0000

Data Index: 698178 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.2899. Min Act: -0.0000

Data Index: 1321662 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.1483. Min Act: -0.0000

Data Index: 1106324 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.0039. Min Act: -0.0000

Data Index: 257109 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.9805. Min Act: -0.0000

Data Index: 235166 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1236747 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.0700. Min Act: -0.0000

Data Index: 281181 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.9445. Min Act: -0.0000

Data Index: 177884 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.7234. Min Range: -2.7234

Max Act: 2.1352. Min Act: -0.0000

Data Index: 319767 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.8802. Min Act: -0.0000

Data Index: 806 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.9766. Min Act: -0.0000

Data Index: 465126 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.9812. Min Act: -0.0000

Data Index: 201394 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.9649. Min Act: -0.0000

Data Index: 234287 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 2.7234. Min Range: -2.7234

Max Act: 1.8465. Min Act: -0.0000

Data Index: 607898 (C4 (Web Text))

Max Activating Token Index: 631