Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.7645. Min Act: -0.0000

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.6409. Min Act: -0.0000

Data Index: 596236 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.3962. Min Act: -0.0000

Data Index: 279623 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.0665. Min Act: -0.0000

Data Index: 1036243 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.3055. Min Act: -0.0000

Data Index: 669707 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.4708. Min Act: -0.0000

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.0942. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.0437. Min Act: -0.0000

Data Index: 1103468 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.5737. Min Act: -0.0000

Data Index: 136710 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9446. Min Act: -0.0000

Data Index: 97731 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 4.7645. Min Range: -4.7645

Max Act: 4.0296. Min Act: -0.0000

Data Index: 481187 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.7933. Min Act: -0.0000

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9540. Min Act: -0.0000

Data Index: 366079 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9344. Min Act: -0.0000

Data Index: 369880 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9718. Min Act: -0.0000

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.6582. Min Act: -0.0000

Data Index: 346975 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9460. Min Act: -0.0000

Data Index: 819083 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.9449. Min Act: -0.0000

Data Index: 226006 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.7905. Min Act: -0.0000

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 4.7645. Min Range: -4.7645

Max Act: 3.5518. Min Act: -0.0001

Data Index: 890671 (C4 (Web Text))

Max Activating Token Index: 54