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

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

Neuron 452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1525131 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1650262 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1410265 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1480533 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1479922 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1499016 (Python Code)

Max Activating Token Index: 247

Text #6

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1521418 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1494476 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1581536 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1409705 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1491971 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1468719 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1400721 (Python Code)

Max Activating Token Index: 448

Text #13

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1617435 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1581252 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1444398 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1513187 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1558825 (Python Code)

Max Activating Token Index: 598

Text #18

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1404008 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6133. Min Act: -0.0001

Data Index: 532823 (C4 (Web Text))

Max Activating Token Index: 284