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

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

Neuron 3209 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.6656. Min Act: -0.0000

Data Index: 548164 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.3168. Min Act: -0.0000

Data Index: 389026 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2503. Min Act: -0.0000

Data Index: 167860 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2000. Min Act: -0.0000

Data Index: 68546 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.4005. Min Act: -0.0000

Data Index: 148950 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.3722. Min Act: -0.0000

Data Index: 972306 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.1186. Min Act: -0.0000

Data Index: 886635 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.4406. Min Act: -0.0000

Data Index: 473631 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2382. Min Act: -0.0000

Data Index: 133200 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1189792 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2252. Min Act: -0.0000

Data Index: 1329585 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2160. Min Act: -0.0000

Data Index: 552196 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.0814. Min Act: -0.0000

Data Index: 603904 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2153. Min Act: -0.0000

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.2284. Min Act: -0.0000

Data Index: 313473 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 2.6656. Min Range: -2.6656

Max Act: 1.9808. Min Act: -0.0000

Data Index: 577538 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 2.6656. Min Range: -2.6656

Max Act: 2.0667. Min Act: -0.0000

Data Index: 1084649 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.6656. Min Range: -2.6656

Max Act: 1.9291. Min Act: -0.0000

Data Index: 1081301 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 2.6656. Min Range: -2.6656

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1311894 (C4 (Web Text))

Max Activating Token Index: 206