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

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

Neuron 3038 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.8559. Min Act: -0.0000

Data Index: 676992 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7978. Min Act: -0.0000

Data Index: 88638 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1292418 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7349. Min Act: -0.0000

Data Index: 868842 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1232202 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7010. Min Act: -0.0000

Data Index: 243362 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.8021. Min Act: -0.0000

Data Index: 678538 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1061652 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7657. Min Act: -0.0000

Data Index: 356079 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1234061 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1137690 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6767. Min Act: -0.0000

Data Index: 923124 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.7451. Min Act: -0.0000

Data Index: 432571 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6710. Min Act: -0.0000

Data Index: 7043 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6096. Min Act: -0.0000

Data Index: 350580 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6377. Min Act: -0.0000

Data Index: 545340 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.6039. Min Act: 0.0000

Data Index: 858318 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.5980. Min Act: -0.0000

Data Index: 402202 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1225802 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.8559. Min Range: -0.8559

Max Act: 0.5729. Min Act: -0.0000

Data Index: 679453 (C4 (Web Text))

Max Activating Token Index: 791