Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 752 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1642102 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1587412 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6559. Min Act: -0.0001

Data Index: 1479192 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6730. Min Act: -0.0001

Data Index: 1401661 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1496679 (Python Code)

Max Activating Token Index: 374

Text #5

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6280. Min Act: -0.0001

Data Index: 1453181 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1606517 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6606. Min Act: -0.0001

Data Index: 1520105 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1649603 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1399600 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1577842 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6372. Min Act: -0.0001

Data Index: 1571437 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1647256 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6353. Min Act: -0.0001

Data Index: 1440337 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6128. Min Act: -0.0001

Data Index: 1480925 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1616508 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5910. Min Act: -0.0001

Data Index: 1384220 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1645373 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6066. Min Act: -0.0001

Data Index: 1370891 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5836. Min Act: -0.0001

Data Index: 1521810 (Python Code)

Max Activating Token Index: 141