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

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

Neuron 2735 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: 1.5071. Min Range: -1.5071

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1363859 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1651517 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1653372 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1426349 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1496671 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1520685 (Python Code)

Max Activating Token Index: 943

Text #6

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1648054 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1426365 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1581026 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1443327 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1398855 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1505495 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1602175 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.5071. Min Range: -1.5071

Max Act: 0.8695. Min Act: -0.0000

Data Index: 819570 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1359874 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1375080 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1425059 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1411440 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 1.5071. Min Range: -1.5071

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1532438 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 1.5071. Min Range: -1.5071

Max Act: 0.9315. Min Act: -0.0000

Data Index: 196081 (C4 (Web Text))

Max Activating Token Index: 871