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

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

Neuron 3643 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.9946. Min Act: -0.0000

Data Index: 1412203 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7627. Min Act: -0.0000

Data Index: 1628845 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7308. Min Act: -0.0000

Data Index: 1522806 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1498427 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.4629. Min Act: -0.0000

Data Index: 1616591 (Python Code)

Max Activating Token Index: 354

Text #5

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.5676. Min Act: -0.0000

Data Index: 1407430 (Python Code)

Max Activating Token Index: 1014

Text #6

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1435122 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.4739. Min Act: -0.0000

Data Index: 1612909 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.2651. Min Act: -0.0000

Data Index: 1367218 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.4859. Min Act: -0.0000

Data Index: 165513 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.2286. Min Act: -0.0000

Data Index: 1637180 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.3533. Min Act: -0.0000

Data Index: 1580511 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.3305. Min Act: -0.0000

Data Index: 1596001 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.4431. Min Act: -0.0000

Data Index: 1641022 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.2298. Min Act: -0.0000

Data Index: 1428287 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1533546 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.3702. Min Act: -0.0000

Data Index: 1602227 (Python Code)

Max Activating Token Index: 202

Text #17

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.3794. Min Act: -0.0000

Data Index: 1591687 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.2584. Min Act: -0.0000

Data Index: 1436662 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.1813. Min Act: -0.0000

Data Index: 1406010 (Python Code)

Max Activating Token Index: 330