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

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

Neuron 1551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1249395 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4947. Min Act: -0.0000

Data Index: 44778 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1603464 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1438202 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1620679 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1604698 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1594080 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1535188 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1647990 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1657101 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1520000 (Python Code)

Max Activating Token Index: 410

Text #11

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1567190 (Python Code)

Max Activating Token Index: 379

Text #12

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1404724 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1440321 (Python Code)

Max Activating Token Index: 591

Text #14

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1362641 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4617. Min Act: -0.0000

Data Index: 399159 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1561110 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1429413 (Python Code)

Max Activating Token Index: 839

Text #18

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1522228 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 0.5191. Min Range: -0.5191

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1599006 (Python Code)

Max Activating Token Index: 467