Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.8985. Min Act: -0.0000

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.8891. Min Act: -0.0000

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7775. Min Act: -0.0000

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7566. Min Act: -0.0000

Data Index: 16481 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7716. Min Act: -0.0000

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7667. Min Act: -0.0000

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7288. Min Act: -0.0000

Data Index: 677651 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7341. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6426. Min Act: -0.0000

Data Index: 28721 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1284024 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6422. Min Act: -0.0000

Data Index: 485608 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6454. Min Act: -0.0000

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6345. Min Act: -0.0000

Data Index: 25168 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1138918 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6263. Min Act: -0.0000

Data Index: 143536 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6041. Min Act: -0.0000

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5859. Min Act: -0.0000

Data Index: 500578 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5615. Min Act: -0.0000

Data Index: 715800 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5513. Min Act: -0.0000

Data Index: 378648 (C4 (Web Text))

Max Activating Token Index: 688