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

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

Neuron 3795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.7400. Min Act: -0.0000

Data Index: 1591258 (Python Code)

Max Activating Token Index: 888

Text #1

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.3440. Min Act: -0.0000

Data Index: 1520810 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.3437. Min Act: -0.0000

Data Index: 1443735 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1488187 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4276. Min Act: -0.0000

Data Index: 1403833 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.6817. Min Act: -0.0000

Data Index: 1597369 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.5390. Min Act: -0.0000

Data Index: 1416477 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4769. Min Act: -0.0000

Data Index: 1528717 (Python Code)

Max Activating Token Index: 701

Text #8

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.5987. Min Act: -0.0000

Data Index: 1523053 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.3354. Min Act: -0.0000

Data Index: 1440619 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1565144 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4635. Min Act: -0.0000

Data Index: 1654924 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4683. Min Act: -0.0000

Data Index: 1629506 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1647887 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1598103 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4486. Min Act: -0.0000

Data Index: 1476523 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.5706. Min Act: -0.0000

Data Index: 1621244 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1510345 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4476. Min Act: -0.0000

Data Index: 1406634 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.7400. Min Range: -2.7400

Max Act: 2.4286. Min Act: -0.0000

Data Index: 1520235 (Python Code)

Max Activating Token Index: 662