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

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

Neuron 4636 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.1775. Min Act: -0.0000

Data Index: 983495 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0709. Min Act: -0.0000

Data Index: 109725 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0314. Min Act: -0.0000

Data Index: 831168 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9192. Min Act: -0.0000

Data Index: 676000 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9704. Min Act: -0.0000

Data Index: 219148 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0250. Min Act: -0.0000

Data Index: 155418 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8965. Min Act: -0.0000

Data Index: 946532 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1103580 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9939. Min Act: -0.0000

Data Index: 238232 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9137. Min Act: -0.0000

Data Index: 252265 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9388. Min Act: -0.0000

Data Index: 206335 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8746. Min Act: -0.0000

Data Index: 911628 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8755. Min Act: -0.0000

Data Index: 506486 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8563. Min Act: -0.0000

Data Index: 652913 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9082. Min Act: -0.0000

Data Index: 901808 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8468. Min Act: -0.0000

Data Index: 416919 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8454. Min Act: -0.0000

Data Index: 877816 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1008934 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 579