Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2603. Min Act: -0.0001

Data Index: 221739 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2407. Min Act: -0.0001

Data Index: 760272 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2574. Min Act: -0.0001

Data Index: 93364 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1221324 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2378. Min Act: -0.0001

Data Index: 527099 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1079338 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2246. Min Act: -0.0001

Data Index: 548169 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2364. Min Act: -0.0001

Data Index: 315182 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1109557 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2236. Min Act: -0.0001

Data Index: 239606 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2261. Min Act: -0.0001

Data Index: 180035 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2029. Min Act: -0.0001

Data Index: 566839 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2304. Min Act: -0.0001

Data Index: 834278 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1428633 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1572094 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1362772 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1580075 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2258. Min Act: -0.0001

Data Index: 483399 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2179. Min Act: -0.0001

Data Index: 32867 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1184826 (C4 (Web Text))

Max Activating Token Index: 384