Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1095724 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1463. Min Act: -0.0001

Data Index: 737544 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1498. Min Act: -0.0001

Data Index: 532967 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0780. Min Act: -0.0001

Data Index: 899518 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9883. Min Act: -0.0001

Data Index: 898097 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0438. Min Act: -0.0001

Data Index: 85875 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0615. Min Act: -0.0001

Data Index: 521945 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1318279 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0659. Min Act: -0.0001

Data Index: 1261532 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0373. Min Act: -0.0001

Data Index: 429161 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0328. Min Act: -0.0001

Data Index: 865711 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0227. Min Act: -0.0001

Data Index: 1058050 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9776. Min Act: -0.0001

Data Index: 120802 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9582. Min Act: -0.0001

Data Index: 237512 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9100. Min Act: -0.0001

Data Index: 752985 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9110. Min Act: -0.0001

Data Index: 1191363 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9629. Min Act: -0.0001

Data Index: 6573 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9337. Min Act: -0.0001

Data Index: 527006 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9583. Min Act: -0.0001

Data Index: 468125 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9133. Min Act: -0.0001

Data Index: 255361 (C4 (Web Text))

Max Activating Token Index: 320