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

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

Neuron 5308 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1236663 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.3373. Min Act: -0.0000

Data Index: 572845 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.2237. Min Act: -0.0000

Data Index: 442040 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1078091 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1337993 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.9252. Min Range: -1.9252

Max Act: 1.0385. Min Act: -0.0000

Data Index: 293242 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9229. Min Act: -0.0000

Data Index: 263047 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9183. Min Act: -0.0000

Data Index: 881513 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1046080 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9366. Min Act: -0.0000

Data Index: 918830 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9394. Min Act: -0.0000

Data Index: 92637 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9198. Min Act: -0.0000

Data Index: 496692 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9684. Min Act: -0.0000

Data Index: 893937 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.9018. Min Act: -0.0000

Data Index: 512145 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8198. Min Act: -0.0000

Data Index: 179225 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1274695 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8511. Min Act: -0.0000

Data Index: 614151 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8424. Min Act: -0.0000

Data Index: 621294 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8350. Min Act: -0.0000

Data Index: 682293 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.9252. Min Range: -1.9252

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1192661 (C4 (Web Text))

Max Activating Token Index: 184