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

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

Neuron 5258 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2243. Min Range: -2.2243

Max Act: 2.2243. Min Act: -0.0000

Data Index: 749287 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.8757. Min Act: -0.0000

Data Index: 947874 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.9438. Min Act: -0.0000

Data Index: 803536 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 2.2243. Min Range: -2.2243

Max Act: 2.0565. Min Act: -0.0000

Data Index: 270596 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.9120. Min Act: -0.0000

Data Index: 1210017 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.8807. Min Act: -0.0000

Data Index: 643540 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.8500. Min Act: -0.0000

Data Index: 1054654 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.8522. Min Act: -0.0000

Data Index: 678178 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.7927. Min Act: -0.0000

Data Index: 150985 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.7817. Min Act: -0.0000

Data Index: 997809 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.7553. Min Act: -0.0000

Data Index: 477025 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6534. Min Act: -0.0000

Data Index: 928534 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.7394. Min Act: -0.0000

Data Index: 361435 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6304. Min Act: -0.0000

Data Index: 812494 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6232. Min Act: -0.0000

Data Index: 264878 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1278647 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.7696. Min Act: -0.0000

Data Index: 898226 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1043895 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.5711. Min Act: -0.0000

Data Index: 246483 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 2.2243. Min Range: -2.2243

Max Act: 1.6560. Min Act: -0.0000

Data Index: 980730 (C4 (Web Text))

Max Activating Token Index: 151