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

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

Neuron 2554 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: 0.3274. Min Range: -0.3274

Max Act: 0.3274. Min Act: -0.0000

Data Index: 560322 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3012. Min Act: 0.0000

Data Index: 238268 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1120903 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2603. Min Act: -0.0000

Data Index: 392427 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2345. Min Act: 0.0000

Data Index: 403075 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1279930 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1059521 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2469. Min Act: -0.0000

Data Index: 399662 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1044252 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2249. Min Act: 0.0000

Data Index: 1181907 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2366. Min Act: 0.0000

Data Index: 647466 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2321. Min Act: 0.0000

Data Index: 267505 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2420. Min Act: -0.0000

Data Index: 804227 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2463. Min Act: -0.0000

Data Index: 85709 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1197417 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2386. Min Act: -0.0000

Data Index: 216191 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2355. Min Act: -0.0000

Data Index: 138324 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2444. Min Act: -0.0000

Data Index: 905345 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1286166 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2334. Min Act: -0.0000

Data Index: 680059 (C4 (Web Text))

Max Activating Token Index: 710