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

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

Neuron 128 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: 4.4566. Min Range: -4.4566

Max Act: 4.4002. Min Act: -0.0001

Data Index: 939112 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 4.4566. Min Range: -4.4566

Max Act: 4.4566. Min Act: -0.0001

Data Index: 718704 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.7217. Min Act: -0.0001

Data Index: 751018 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.6734. Min Act: -0.0001

Data Index: 717329 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.8281. Min Act: -0.0001

Data Index: 235899 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.4541. Min Act: -0.0001

Data Index: 530364 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.5435. Min Act: -0.0001

Data Index: 1111833 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0864. Min Act: -0.0001

Data Index: 433501 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.1998. Min Act: -0.0001

Data Index: 168725 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0069. Min Act: -0.0001

Data Index: 828658 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.2334. Min Act: -0.0001

Data Index: 518123 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0906. Min Act: -0.0001

Data Index: 861010 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.5331. Min Act: -0.0001

Data Index: 674655 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0732. Min Act: -0.0001

Data Index: 1193834 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.2189. Min Act: -0.0001

Data Index: 1335519 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0295. Min Act: -0.0001

Data Index: 1108115 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.1479. Min Act: -0.0001

Data Index: 99402 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.1483. Min Act: -0.0001

Data Index: 1133983 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 4.4566. Min Range: -4.4566

Max Act: 3.0837. Min Act: -0.0001

Data Index: 465123 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 4.4566. Min Range: -4.4566

Max Act: 2.7651. Min Act: -0.0001

Data Index: 1071176 (C4 (Web Text))

Max Activating Token Index: 478