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

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

Neuron 3000 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: 0.3882. Min Range: -0.3882

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1248469 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3265. Min Act: -0.0001

Data Index: 375324 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2686. Min Act: -0.0001

Data Index: 863967 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2630. Min Act: -0.0001

Data Index: 757363 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2528. Min Act: -0.0001

Data Index: 396483 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2589. Min Act: -0.0001

Data Index: 268559 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2401. Min Act: -0.0000

Data Index: 15252 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2564. Min Act: -0.0000

Data Index: 260076 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2551. Min Act: -0.0001

Data Index: 958619 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2438. Min Act: -0.0001

Data Index: 48301 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1051618 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2530. Min Act: -0.0001

Data Index: 526543 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1282511 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1170446 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1038277 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1192423 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2468. Min Act: -0.0001

Data Index: 691654 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2524. Min Act: -0.0001

Data Index: 197198 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2412. Min Act: -0.0001

Data Index: 629500 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2295. Min Act: -0.0001

Data Index: 657767 (C4 (Web Text))

Max Activating Token Index: 347