Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2889 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4134. Min Range: -5.4134

Max Act: 5.4134. Min Act: -0.0000

Data Index: 1505341 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 5.4134. Min Range: -5.4134

Max Act: 4.4041. Min Act: -0.0000

Data Index: 1578725 (Python Code)

Max Activating Token Index: 331

Text #2

Max Range: 5.4134. Min Range: -5.4134

Max Act: 4.2210. Min Act: -0.0000

Data Index: 1590139 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 5.4134. Min Range: -5.4134

Max Act: 4.0931. Min Act: -0.0000

Data Index: 1587407 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.9168. Min Act: -0.0000

Data Index: 1363935 (Python Code)

Max Activating Token Index: 798

Text #5

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.6377. Min Act: -0.0000

Data Index: 1468918 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.8128. Min Act: -0.0000

Data Index: 1520403 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.5969. Min Act: -0.0000

Data Index: 1638781 (Python Code)

Max Activating Token Index: 401

Text #8

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.7194. Min Act: -0.0000

Data Index: 1506911 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.7212. Min Act: -0.0000

Data Index: 1601159 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.6678. Min Act: -0.0000

Data Index: 1451883 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.5059. Min Act: -0.0000

Data Index: 1631600 (Python Code)

Max Activating Token Index: 528

Text #12

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.7871. Min Act: -0.0000

Data Index: 1438438 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.6127. Min Act: -0.0000

Data Index: 1643357 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.8051. Min Act: -0.0000

Data Index: 1595516 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.7438. Min Act: -0.0000

Data Index: 1573864 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.7055. Min Act: -0.0000

Data Index: 1485894 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.6984. Min Act: -0.0000

Data Index: 1635885 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.6331. Min Act: -0.0000

Data Index: 1587933 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 5.4134. Min Range: -5.4134

Max Act: 3.3062. Min Act: -0.0000

Data Index: 828333 (C4 (Web Text))

Max Activating Token Index: 814