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

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

Neuron 3245 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: 1.1047. Min Range: -1.1047

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1653823 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1429566 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9131. Min Act: -0.0001

Data Index: 1382609 (Python Code)

Max Activating Token Index: 788

Text #3

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1597828 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1422989 (Python Code)

Max Activating Token Index: 486

Text #5

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8280. Min Act: -0.0002

Data Index: 1359910 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8107. Min Act: -0.0002

Data Index: 1594149 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8591. Min Act: -0.0001

Data Index: 1634157 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1651688 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8193. Min Act: -0.0001

Data Index: 1633604 (Python Code)

Max Activating Token Index: 426

Text #10

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1528208 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8378. Min Act: -0.0002

Data Index: 1404219 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.7884. Min Act: -0.0002

Data Index: 1378189 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1478172 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8432. Min Act: -0.0001

Data Index: 1502457 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1617110 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1577374 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.7949. Min Act: -0.0001

Data Index: 1391645 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.7423. Min Act: -0.0001

Data Index: 1522845 (Python Code)

Max Activating Token Index: 118

Text #19

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1429025 (Python Code)

Max Activating Token Index: 22