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

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

Neuron 1726 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1276099 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.4865. Min Act: -0.0001

Data Index: 781293 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.4442. Min Act: -0.0001

Data Index: 127081 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.4455. Min Act: -0.0001

Data Index: 300748 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3484. Min Act: -0.0001

Data Index: 1161275 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3330. Min Act: -0.0001

Data Index: 5233 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3241. Min Act: -0.0001

Data Index: 205665 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3870. Min Act: -0.0001

Data Index: 573803 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3482. Min Act: -0.0001

Data Index: 950908 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3401. Min Act: -0.0001

Data Index: 867949 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1652060 (Python Code)

Max Activating Token Index: 459

Text #11

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3462. Min Act: -0.0002

Data Index: 599288 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3432. Min Act: -0.0001

Data Index: 892737 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1557003 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.2986. Min Act: -0.0001

Data Index: 19003 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3138. Min Act: -0.0001

Data Index: 214719 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1203196 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1010421 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1412104 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 0.5729. Min Range: -0.5729

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1650715 (Python Code)

Max Activating Token Index: 14