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

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

Neuron 5705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.0000

Data Index: 284693 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5761. Min Act: -0.0000

Data Index: 491207 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1057777 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4462. Min Act: -0.0000

Data Index: 624457 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4140. Min Act: -0.0000

Data Index: 6156 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3647. Min Act: -0.0000

Data Index: 778791 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1237485 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2971. Min Act: -0.0000

Data Index: 988486 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2924. Min Act: -0.0000

Data Index: 13798 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.1986. Min Act: -0.0000

Data Index: 386865 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3456. Min Act: -0.0000

Data Index: 968817 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2329. Min Act: -0.0000

Data Index: 345911 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2184. Min Act: -0.0000

Data Index: 627196 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2203. Min Act: -0.0000

Data Index: 810821 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2753. Min Act: -0.0000

Data Index: 255687 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1253122 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2133. Min Act: -0.0000

Data Index: 798232 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2040. Min Act: -0.0000

Data Index: 518380 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2020. Min Act: -0.0000

Data Index: 538274 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.1872. Min Act: -0.0000

Data Index: 872731 (C4 (Web Text))

Max Activating Token Index: 141