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

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

Neuron 342 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0003

Data Index: 312935 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0619. Min Act: -0.0003

Data Index: 857016 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0539. Min Act: -0.0003

Data Index: 181221 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0491. Min Act: -0.0003

Data Index: 658627 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0523. Min Act: -0.0003

Data Index: 623697 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0516. Min Act: -0.0003

Data Index: 605826 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0512. Min Act: -0.0003

Data Index: 339701 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0493. Min Act: -0.0003

Data Index: 945760 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0488. Min Act: -0.0003

Data Index: 545578 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1231417 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0477. Min Act: -0.0003

Data Index: 83199 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0493. Min Act: -0.0004

Data Index: 240227 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0446. Min Act: -0.0003

Data Index: 12764 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0456. Min Act: -0.0003

Data Index: 374257 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1156982 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0435. Min Act: -0.0003

Data Index: 885907 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0454. Min Act: -0.0003

Data Index: 207865 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1155725 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1345844 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1021102 (C4 (Web Text))

Max Activating Token Index: 803