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

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

Neuron 2321 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: 1.2275. Min Range: -1.2275

Max Act: 1.0841. Min Act: -0.0001

Data Index: 668329 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.2275. Min Act: -0.0001

Data Index: 960411 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0307. Min Act: -0.0001

Data Index: 154776 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0376. Min Act: -0.0001

Data Index: 444880 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8631. Min Act: -0.0001

Data Index: 360259 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1367. Min Act: -0.0001

Data Index: 445153 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8572. Min Act: -0.0001

Data Index: 110252 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9251. Min Act: -0.0001

Data Index: 860019 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9241. Min Act: -0.0001

Data Index: 480476 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8659. Min Act: -0.0001

Data Index: 1010266 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8270. Min Act: -0.0001

Data Index: 776840 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9220. Min Act: -0.0001

Data Index: 847805 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9352. Min Act: -0.0001

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8890. Min Act: -0.0001

Data Index: 331511 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8635. Min Act: -0.0001

Data Index: 14680 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8578. Min Act: -0.0001

Data Index: 1154560 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9032. Min Act: -0.0001

Data Index: 1344545 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1340067 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8725. Min Act: -0.0001

Data Index: 1105011 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9552. Min Act: -0.0001

Data Index: 264412 (C4 (Web Text))

Max Activating Token Index: 100