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

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

Neuron 4683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.3124. Min Act: -0.0000

Data Index: 1636918 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1365483 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1086. Min Act: -0.0000

Data Index: 142179 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1447604 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1436770 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1904. Min Act: -0.0000

Data Index: 1401195 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.0715. Min Act: -0.0000

Data Index: 1434873 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1570619 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1338. Min Act: -0.0000

Data Index: 969409 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.1107. Min Act: -0.0000

Data Index: 1600168 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.0937. Min Act: -0.0000

Data Index: 1375346 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 2.3124. Min Range: -2.3124

Max Act: 2.0913. Min Act: -0.0000

Data Index: 483965 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.9890. Min Act: -0.0000

Data Index: 1611914 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.8692. Min Act: -0.0000

Data Index: 1654361 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.9634. Min Act: -0.0000

Data Index: 1460020 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.9230. Min Act: -0.0000

Data Index: 198796 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1115238 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1339220 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.8757. Min Act: -0.0000

Data Index: 53322 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 2.3124. Min Range: -2.3124

Max Act: 1.9914. Min Act: -0.0000

Data Index: 1634849 (Python Code)

Max Activating Token Index: 398