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

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

Neuron 1421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9539. Min Act: -0.0001

Data Index: 70550 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9555. Min Act: -0.0001

Data Index: 631826 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9305. Min Act: -0.0001

Data Index: 836949 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1520924 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6884. Min Act: -0.0001

Data Index: 633267 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6642. Min Act: -0.0001

Data Index: 559465 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6848. Min Act: -0.0001

Data Index: 65333 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7094. Min Act: -0.0001

Data Index: 277077 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6690. Min Act: -0.0001

Data Index: 1503828 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7111. Min Act: -0.0001

Data Index: 56773 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6690. Min Act: -0.0001

Data Index: 1015603 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6736. Min Act: -0.0001

Data Index: 90416 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6650. Min Act: -0.0001

Data Index: 683383 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6943. Min Act: -0.0001

Data Index: 1030763 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6501. Min Act: -0.0001

Data Index: 466662 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6447. Min Act: -0.0001

Data Index: 410179 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6408. Min Act: -0.0001

Data Index: 175206 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6773. Min Act: -0.0001

Data Index: 829342 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5999. Min Act: -0.0001

Data Index: 342778 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6568. Min Act: -0.0001

Data Index: 317465 (C4 (Web Text))

Max Activating Token Index: 183