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

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

Neuron 3964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1277. Min Act: -0.0001

Data Index: 666961 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0898. Min Act: -0.0001

Data Index: 505465 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0901. Min Act: -0.0001

Data Index: 463002 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1040602 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1313935 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0704. Min Act: -0.0000

Data Index: 875689 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1310691 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0538. Min Act: -0.0001

Data Index: 713348 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0638. Min Act: -0.0000

Data Index: 145677 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0611. Min Act: -0.0001

Data Index: 576866 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0579. Min Act: -0.0001

Data Index: 298765 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1220182 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1001658 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1005623 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0570. Min Act: -0.0001

Data Index: 276570 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0561. Min Act: -0.0000

Data Index: 465464 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0542. Min Act: -0.0001

Data Index: 503430 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0504. Min Act: -0.0000

Data Index: 905119 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1229577 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0577. Min Act: -0.0001

Data Index: 198710 (C4 (Web Text))

Max Activating Token Index: 658