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

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

Neuron 527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1209123 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0743. Min Act: -0.0000

Data Index: 540399 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8898. Min Act: -0.0000

Data Index: 74863 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8715. Min Act: -0.0001

Data Index: 790794 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8408. Min Act: -0.0001

Data Index: 847307 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8515. Min Act: -0.0000

Data Index: 452769 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1260536 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8900. Min Act: -0.0001

Data Index: 1243086 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7683. Min Act: -0.0001

Data Index: 110111 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8028. Min Act: -0.0001

Data Index: 888982 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7701. Min Act: -0.0000

Data Index: 181798 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1155902 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7831. Min Act: -0.0001

Data Index: 1055051 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7590. Min Act: -0.0000

Data Index: 140601 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1329358 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7600. Min Act: -0.0000

Data Index: 490600 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7773. Min Act: -0.0001

Data Index: 196939 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1220113 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8046. Min Act: -0.0000

Data Index: 936638 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.7450. Min Act: -0.0001

Data Index: 33253 (C4 (Web Text))

Max Activating Token Index: 289