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

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

Neuron 4721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8515. Min Range: -4.8515

Max Act: 4.8515. Min Act: -0.0001

Data Index: 260909 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 4.8515. Min Range: -4.8515

Max Act: 4.3547. Min Act: -0.0001

Data Index: 673505 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 4.8515. Min Range: -4.8515

Max Act: 4.2675. Min Act: -0.0001

Data Index: 894777 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 4.8515. Min Range: -4.8515

Max Act: 4.0000. Min Act: -0.0001

Data Index: 803267 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.9791. Min Act: -0.0001

Data Index: 745829 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.8756. Min Act: -0.0001

Data Index: 491569 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.5146. Min Act: -0.0001

Data Index: 292570 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.6357. Min Act: -0.0001

Data Index: 412016 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.6041. Min Act: -0.0001

Data Index: 1291719 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.5906. Min Act: -0.0001

Data Index: 1322605 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.6962. Min Act: -0.0001

Data Index: 1225101 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.4775. Min Act: -0.0001

Data Index: 428266 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.3455. Min Act: -0.0001

Data Index: 882211 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.6170. Min Act: -0.0001

Data Index: 969665 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.3077. Min Act: -0.0001

Data Index: 1224667 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.6657. Min Act: -0.0001

Data Index: 112675 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.3780. Min Act: -0.0001

Data Index: 326467 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.0880. Min Act: -0.0001

Data Index: 892612 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.1934. Min Act: -0.0001

Data Index: 904482 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 4.8515. Min Range: -4.8515

Max Act: 3.3501. Min Act: -0.0001

Data Index: 749703 (C4 (Web Text))

Max Activating Token Index: 804