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

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

Neuron 469 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: 0.8838. Min Range: -0.8838

Max Act: 0.8838. Min Act: -0.0002

Data Index: 1557087 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1464949 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1577594 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1582566 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1592382 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6882. Min Act: -0.0001

Data Index: 1393732 (Python Code)

Max Activating Token Index: 84

Text #6

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1557294 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6261. Min Act: -0.0001

Data Index: 1643521 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6175. Min Act: -0.0001

Data Index: 1483223 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1409492 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1427209 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1466732 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6117. Min Act: -0.0001

Data Index: 1394856 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1392399 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1466447 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1429747 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1630249 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1369844 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5933. Min Act: -0.0001

Data Index: 1385638 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6133. Min Act: -0.0001

Data Index: 1426856 (Python Code)

Max Activating Token Index: 147