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

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

Neuron 3031 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1413608 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4464. Min Act: -0.0001

Data Index: 1631371 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3476. Min Act: -0.0001

Data Index: 1444772 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1368771 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1373226 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1720. Min Act: -0.0001

Data Index: 1491350 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1548046 (Python Code)

Max Activating Token Index: 333

Text #7

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1364984 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1652427 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1533234 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1612602 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1449736 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1435417 (Python Code)

Max Activating Token Index: 762

Text #13

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9948. Min Act: -0.0001

Data Index: 1493488 (Python Code)

Max Activating Token Index: 583

Text #14

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1584415 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1457461 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1467471 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1406330 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 1.4628. Min Range: -1.4628

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1652831 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1522285 (Python Code)

Max Activating Token Index: 263