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

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

Neuron 220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1515797 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3618. Min Act: -0.0001

Data Index: 1180700 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3538. Min Act: -0.0000

Data Index: 228834 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1634313 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3309. Min Act: -0.0001

Data Index: 1570357 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1362772 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3188. Min Act: -0.0001

Data Index: 559122 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1586252 (Python Code)

Max Activating Token Index: 425

Text #8

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1261099 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3235. Min Act: -0.0001

Data Index: 1362295 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3230. Min Act: -0.0000

Data Index: 828493 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1634368 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1117857 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3187. Min Act: -0.0000

Data Index: 236562 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3085. Min Act: -0.0001

Data Index: 800737 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1103656 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2990. Min Act: -0.0001

Data Index: 803034 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3054. Min Act: -0.0000

Data Index: 114481 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3092. Min Act: -0.0001

Data Index: 72642 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1460969 (Python Code)

Max Activating Token Index: 713