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

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

Neuron 284 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0295. Min Act: -0.0002

Data Index: 267500 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1376706 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0298. Min Act: -0.0002

Data Index: 410985 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1018376 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1343741 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1192532 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1180156 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1064147 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1242362 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0291. Min Act: -0.0002

Data Index: 290688 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0279. Min Act: -0.0002

Data Index: 550724 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0002

Data Index: 828976 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0282. Min Act: -0.0002

Data Index: 545593 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1138466 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1048716 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0281. Min Act: -0.0002

Data Index: 732149 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0279. Min Act: -0.0002

Data Index: 386271 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0279. Min Act: -0.0002

Data Index: 798277 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0002

Data Index: 591922 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1291145 (C4 (Web Text))

Max Activating Token Index: 656