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

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

Neuron 3895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2361. Min Range: -1.2361

Max Act: 1.2361. Min Act: -0.0001

Data Index: 619436 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.2361. Min Range: -1.2361

Max Act: 1.1749. Min Act: -0.0001

Data Index: 674808 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.2361. Min Range: -1.2361

Max Act: 1.0700. Min Act: -0.0001

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.2361. Min Range: -1.2361

Max Act: 1.0273. Min Act: -0.0001

Data Index: 345177 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.2361. Min Range: -1.2361

Max Act: 1.0500. Min Act: -0.0001

Data Index: 1196548 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9746. Min Act: -0.0001

Data Index: 862788 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1270137 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1157392 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1239805 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9540. Min Act: -0.0001

Data Index: 933186 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9290. Min Act: -0.0001

Data Index: 487368 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9766. Min Act: -0.0001

Data Index: 799366 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9179. Min Act: -0.0001

Data Index: 200826 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9345. Min Act: -0.0001

Data Index: 970752 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9340. Min Act: -0.0001

Data Index: 612692 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9389. Min Act: -0.0001

Data Index: 946269 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9401. Min Act: -0.0001

Data Index: 246931 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1645212 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.9328. Min Act: -0.0001

Data Index: 936305 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.2361. Min Range: -1.2361

Max Act: 0.8942. Min Act: -0.0001

Data Index: 762602 (C4 (Web Text))

Max Activating Token Index: 531