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

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

Neuron 788 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.4386. Min Act: -0.0001

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.2556. Min Act: -0.0001

Data Index: 1015003 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.2004. Min Act: -0.0001

Data Index: 347164 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.2306. Min Act: -0.0001

Data Index: 1341821 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1622. Min Act: -0.0001

Data Index: 931212 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1459. Min Act: -0.0001

Data Index: 697370 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1379. Min Act: -0.0001

Data Index: 745689 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1342. Min Act: -0.0001

Data Index: 185266 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0499. Min Act: -0.0001

Data Index: 116768 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1583. Min Act: -0.0001

Data Index: 561413 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1444. Min Act: -0.0001

Data Index: 1184935 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0945. Min Act: -0.0001

Data Index: 980778 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0753. Min Act: -0.0001

Data Index: 1148777 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1380. Min Act: -0.0001

Data Index: 1311006 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0635. Min Act: -0.0001

Data Index: 1234852 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0639. Min Act: -0.0001

Data Index: 865074 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9214. Min Act: -0.0001

Data Index: 942545 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.8753. Min Act: -0.0001

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9068. Min Act: -0.0001

Data Index: 790028 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.8091. Min Act: -0.0001

Data Index: 80530 (C4 (Web Text))

Max Activating Token Index: 169