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

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

Neuron 2148 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3505. Min Range: -7.3505

Max Act: 7.3505. Min Act: -0.0000

Data Index: 30643 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 7.3505. Min Range: -7.3505

Max Act: 7.0542. Min Act: -0.0000

Data Index: 1146684 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 7.3505. Min Range: -7.3505

Max Act: 6.7710. Min Act: 0.0000

Data Index: 707160 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 7.3505. Min Range: -7.3505

Max Act: 6.8354. Min Act: -0.0000

Data Index: 1063723 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 7.3505. Min Range: -7.3505

Max Act: 7.1791. Min Act: 0.0000

Data Index: 954719 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 7.3505. Min Range: -7.3505

Max Act: 6.4447. Min Act: 0.0000

Data Index: 40209 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.8951. Min Act: -0.0000

Data Index: 563565 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 7.3505. Min Range: -7.3505

Max Act: 6.2313. Min Act: -0.0000

Data Index: 765861 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 7.3505. Min Range: -7.3505

Max Act: 4.9211. Min Act: -0.0000

Data Index: 579057 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.4407. Min Act: -0.0000

Data Index: 115148 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.4221. Min Act: -0.0000

Data Index: 655383 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.6384. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.6083. Min Act: 0.0000

Data Index: 145028 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.2565. Min Act: 0.0000

Data Index: 780850 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.3917. Min Act: -0.0000

Data Index: 321189 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.1980. Min Act: 0.0000

Data Index: 1065229 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.5541. Min Act: -0.0000

Data Index: 654092 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.1592. Min Act: 0.0001

Data Index: 1212575 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.3263. Min Act: 0.0000

Data Index: 837463 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 7.3505. Min Range: -7.3505

Max Act: 5.4911. Min Act: 0.0000

Data Index: 297399 (C4 (Web Text))

Max Activating Token Index: 371