Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 602 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0005

Data Index: 1411860 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1464939 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1412723 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1418196 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0413. Min Act: -0.0005

Data Index: 1545349 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0373. Min Act: -0.0005

Data Index: 1360026 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1499563 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0353. Min Act: -0.0005

Data Index: 1384857 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1591492 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0340. Min Act: -0.0005

Data Index: 1436324 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0342. Min Act: -0.0005

Data Index: 1535694 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1540876 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1578957 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1632624 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1397034 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0330. Min Act: -0.0005

Data Index: 1440316 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0337. Min Act: -0.0006

Data Index: 1528790 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1467637 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1581891 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1626764 (Python Code)

Max Activating Token Index: 898