Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8714. Min Act: -0.0002

Data Index: 191379 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7321. Min Act: -0.0001

Data Index: 603200 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7348. Min Act: -0.0001

Data Index: 522362 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6886. Min Act: -0.0001

Data Index: 591512 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6833. Min Act: -0.0001

Data Index: 421663 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7278. Min Act: -0.0002

Data Index: 603303 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6606. Min Act: -0.0001

Data Index: 1316317 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6080. Min Act: -0.0002

Data Index: 172149 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6623. Min Act: -0.0001

Data Index: 613706 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6372. Min Act: -0.0001

Data Index: 303492 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7171. Min Act: -0.0001

Data Index: 774207 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6960. Min Act: -0.0001

Data Index: 566998 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6646. Min Act: -0.0001

Data Index: 855662 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6444. Min Act: -0.0002

Data Index: 1245638 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6410. Min Act: -0.0001

Data Index: 189698 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6114. Min Act: -0.0001

Data Index: 1178243 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6466. Min Act: -0.0001

Data Index: 52036 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6448. Min Act: -0.0002

Data Index: 322559 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6824. Min Act: -0.0001

Data Index: 452318 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5302. Min Act: -0.0001

Data Index: 61173 (C4 (Web Text))

Max Activating Token Index: 975