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

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

Neuron 1584 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4467. Min Act: -0.0000

Data Index: 510344 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1284910 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4165. Min Act: -0.0001

Data Index: 670485 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4479. Min Act: -0.0001

Data Index: 399642 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1109088 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4080. Min Act: -0.0000

Data Index: 437013 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3455. Min Act: -0.0001

Data Index: 102149 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3708. Min Act: -0.0000

Data Index: 164990 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1114732 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3724. Min Act: -0.0000

Data Index: 462752 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3695. Min Act: -0.0001

Data Index: 513548 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3574. Min Act: -0.0001

Data Index: 461372 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3611. Min Act: -0.0001

Data Index: 478872 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3628. Min Act: -0.0000

Data Index: 866673 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3701. Min Act: -0.0000

Data Index: 504278 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3166. Min Act: -0.0001

Data Index: 355734 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3702. Min Act: -0.0001

Data Index: 477167 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3609. Min Act: -0.0001

Data Index: 143557 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3415. Min Act: -0.0000

Data Index: 878129 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3107. Min Act: -0.0001

Data Index: 637543 (C4 (Web Text))

Max Activating Token Index: 785