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

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

Neuron 674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.7693. Min Act: -0.0000

Data Index: 567799 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.5840. Min Act: -0.0000

Data Index: 377337 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.4396. Min Act: -0.0000

Data Index: 259957 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1309341 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.4323. Min Act: -0.0000

Data Index: 1238790 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.3157. Min Act: -0.0000

Data Index: 103400 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.3201. Min Act: -0.0000

Data Index: 401396 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.0338. Min Act: -0.0000

Data Index: 288798 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.1380. Min Act: -0.0000

Data Index: 585501 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.2452. Min Act: -0.0000

Data Index: 1224224 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.1237. Min Act: -0.0000

Data Index: 460287 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.0160. Min Act: -0.0000

Data Index: 459198 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 2.7693. Min Range: -2.7693

Max Act: 1.9033. Min Act: -0.0000

Data Index: 210038 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.0774. Min Act: -0.0000

Data Index: 720213 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.0814. Min Act: -0.0000

Data Index: 1159941 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.1632. Min Act: -0.0000

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 2.7693. Min Range: -2.7693

Max Act: 1.9216. Min Act: -0.0000

Data Index: 545184 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.7693. Min Range: -2.7693

Max Act: 2.0336. Min Act: -0.0000

Data Index: 733242 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 2.7693. Min Range: -2.7693

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.7693. Min Range: -2.7693

Max Act: 1.9888. Min Act: -0.0000

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 516