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

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

Neuron 2502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0880. Min Act: -0.0001

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0519. Min Act: -0.0001

Data Index: 249045 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0822. Min Act: -0.0001

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0717. Min Act: -0.0001

Data Index: 1175236 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0586. Min Act: -0.0001

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.1420. Min Act: -0.0001

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0386. Min Act: -0.0001

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0314. Min Act: -0.0001

Data Index: 119396 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0995. Min Act: -0.0001

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9952. Min Act: -0.0001

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0018. Min Act: -0.0001

Data Index: 252057 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0303. Min Act: -0.0001

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0238. Min Act: -0.0001

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9611. Min Act: -0.0001

Data Index: 1278501 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9838. Min Act: -0.0001

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9826. Min Act: -0.0001

Data Index: 870781 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9702. Min Act: -0.0001

Data Index: 637338 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9381. Min Act: -0.0001

Data Index: 820793 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9634. Min Act: -0.0001

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 303