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

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

Neuron 3135 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2242. Min Range: -2.2242

Max Act: 2.1418. Min Act: -0.0001

Data Index: 1381377 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 2.2242. Min Range: -2.2242

Max Act: 2.2242. Min Act: -0.0000

Data Index: 1406566 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 2.2242. Min Range: -2.2242

Max Act: 2.1764. Min Act: -0.0000

Data Index: 907154 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.9007. Min Act: -0.0000

Data Index: 775477 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.6491. Min Act: -0.0000

Data Index: 820218 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1600275 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.7161. Min Act: -0.0001

Data Index: 1403514 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.6892. Min Act: -0.0000

Data Index: 1557301 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5755. Min Act: -0.0000

Data Index: 460956 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1504330 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1122656 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1223099 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5040. Min Act: -0.0000

Data Index: 107885 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.4838. Min Act: -0.0000

Data Index: 133879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.3872. Min Act: -0.0001

Data Index: 1570025 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1566458 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5085. Min Act: -0.0000

Data Index: 1607650 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1360961 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1558838 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 2.2242. Min Range: -2.2242

Max Act: 1.5165. Min Act: -0.0001

Data Index: 1644420 (Python Code)

Max Activating Token Index: 206