Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 409 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2751. Min Act: -0.0002

Data Index: 574196 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2562. Min Act: -0.0002

Data Index: 1076655 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2603. Min Act: -0.0002

Data Index: 712049 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2663. Min Act: -0.0002

Data Index: 1354328 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2501. Min Act: -0.0002

Data Index: 524165 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2409. Min Act: -0.0002

Data Index: 586587 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2319. Min Act: -0.0002

Data Index: 1030998 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2358. Min Act: -0.0002

Data Index: 1297293 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2286. Min Act: -0.0002

Data Index: 301250 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1346399 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2380. Min Act: -0.0002

Data Index: 1162650 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2372. Min Act: -0.0002

Data Index: 54514 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2233. Min Act: -0.0002

Data Index: 834460 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2202. Min Act: -0.0002

Data Index: 341025 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2329. Min Act: -0.0002

Data Index: 613630 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2233. Min Act: -0.0002

Data Index: 742011 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2104. Min Act: -0.0002

Data Index: 242786 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2300. Min Act: -0.0002

Data Index: 372810 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2220. Min Act: -0.0001

Data Index: 459189 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2265. Min Act: -0.0002

Data Index: 443285 (C4 (Web Text))

Max Activating Token Index: 429