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

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

Neuron 2036 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0002

Data Index: 211187 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0625. Min Act: -0.0002

Data Index: 582464 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0590. Min Act: -0.0002

Data Index: 70194 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1260776 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0605. Min Act: -0.0003

Data Index: 671886 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0565. Min Act: -0.0003

Data Index: 338549 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1024934 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0551. Min Act: -0.0002

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0511. Min Act: -0.0002

Data Index: 222601 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0499. Min Act: -0.0002

Data Index: 249289 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0504. Min Act: -0.0002

Data Index: 553624 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0500. Min Act: -0.0003

Data Index: 372533 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0505. Min Act: -0.0002

Data Index: 884470 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0494. Min Act: -0.0002

Data Index: 681335 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0499. Min Act: -0.0002

Data Index: 62808 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1567256 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0506. Min Act: -0.0002

Data Index: 219255 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0497. Min Act: -0.0002

Data Index: 984761 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1280541 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0483. Min Act: -0.0002

Data Index: 54646 (C4 (Web Text))

Max Activating Token Index: 69