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

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

Neuron 4279 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: 2.9418. Min Range: -2.9418

Max Act: 2.9418. Min Act: -0.0001

Data Index: 1123099 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.7987. Min Act: -0.0001

Data Index: 674468 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.7511. Min Act: -0.0001

Data Index: 102246 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.4402. Min Act: -0.0000

Data Index: 692451 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.3077. Min Act: -0.0001

Data Index: 608404 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.0983. Min Act: -0.0000

Data Index: 190995 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 2.9418. Min Range: -2.9418

Max Act: 1.9646. Min Act: -0.0000

Data Index: 421761 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.3419. Min Act: -0.0001

Data Index: 90154 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.1793. Min Act: -0.0000

Data Index: 1343360 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.2319. Min Act: -0.0001

Data Index: 1180191 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.1198. Min Act: -0.0000

Data Index: 777371 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.1201. Min Act: -0.0001

Data Index: 654130 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.9418. Min Range: -2.9418

Max Act: 1.9932. Min Act: -0.0000

Data Index: 940251 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.0895. Min Act: -0.0001

Data Index: 1253349 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.1034. Min Act: -0.0000

Data Index: 122170 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.2023. Min Act: -0.0001

Data Index: 732335 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.0799. Min Act: -0.0001

Data Index: 980140 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.1941. Min Act: -0.0000

Data Index: 153787 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 2.9418. Min Range: -2.9418

Max Act: 2.0826. Min Act: -0.0001

Data Index: 988537 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 2.9418. Min Range: -2.9418

Max Act: 1.9540. Min Act: -0.0001

Data Index: 380772 (C4 (Web Text))

Max Activating Token Index: 939