Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4428 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3191. Min Range: -5.3191

Max Act: 4.7361. Min Act: -0.0000

Data Index: 1585565 (Python Code)

Max Activating Token Index: 775

Text #1

Max Range: 5.3191. Min Range: -5.3191

Max Act: 5.3191. Min Act: -0.0000

Data Index: 1550545 (Python Code)

Max Activating Token Index: 380

Text #2

Max Range: 5.3191. Min Range: -5.3191

Max Act: 4.1136. Min Act: -0.0000

Data Index: 1528189 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.7834. Min Act: -0.0000

Data Index: 1381710 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.9297. Min Act: -0.0000

Data Index: 1528151 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 5.3191. Min Range: -5.3191

Max Act: 4.0090. Min Act: -0.0000

Data Index: 1653062 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.5948. Min Act: -0.0000

Data Index: 1545498 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.5501. Min Act: -0.0000

Data Index: 1634941 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 5.3191. Min Range: -5.3191

Max Act: 4.1876. Min Act: -0.0000

Data Index: 1593450 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.5290. Min Act: -0.0000

Data Index: 1536109 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.5579. Min Act: -0.0000

Data Index: 1435870 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1419776 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.4918. Min Act: -0.0000

Data Index: 1406330 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.3246. Min Act: -0.0000

Data Index: 1372032 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.2679. Min Act: -0.0000

Data Index: 1465622 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.7603. Min Act: -0.0000

Data Index: 1419238 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.4187. Min Act: -0.0000

Data Index: 1620892 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.7208. Min Act: -0.0000

Data Index: 1540463 (Python Code)

Max Activating Token Index: 598

Text #18

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.6950. Min Act: -0.0000

Data Index: 1458309 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 5.3191. Min Range: -5.3191

Max Act: 3.3395. Min Act: -0.0000

Data Index: 1585905 (Python Code)

Max Activating Token Index: 659