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

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

Neuron 3016 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.3559. Min Act: -0.0002

Data Index: 906078 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.3757. Min Act: -0.0002

Data Index: 151394 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.3191. Min Act: -0.0002

Data Index: 33015 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.3248. Min Act: -0.0002

Data Index: 565337 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2110. Min Act: -0.0002

Data Index: 1112881 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2961. Min Act: -0.0002

Data Index: 202811 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2608. Min Act: -0.0002

Data Index: 991851 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2121. Min Act: -0.0002

Data Index: 517420 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2004. Min Act: -0.0002

Data Index: 1127826 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1321. Min Act: -0.0002

Data Index: 401682 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2444. Min Act: -0.0002

Data Index: 1154845 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2981. Min Act: -0.0002

Data Index: 964166 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.0681. Min Act: -0.0002

Data Index: 216136 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1647. Min Act: -0.0002

Data Index: 1328878 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.2085. Min Act: -0.0002

Data Index: 411047 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1700. Min Act: -0.0002

Data Index: 1136068 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1161. Min Act: -0.0002

Data Index: 775077 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1740. Min Act: -0.0002

Data Index: 436027 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1247. Min Act: -0.0002

Data Index: 653834 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 1.3757. Min Range: -1.3757

Max Act: 1.1240. Min Act: -0.0002

Data Index: 921913 (C4 (Web Text))

Max Activating Token Index: 406