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

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

Neuron 4736 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: 2.0195. Min Range: -2.0195

Max Act: 2.0195. Min Act: 0.0000

Data Index: 683278 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.7870. Min Act: -0.0000

Data Index: 796153 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.6721. Min Act: -0.0000

Data Index: 478206 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.5293. Min Act: 0.0000

Data Index: 128279 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.2536. Min Act: 0.0000

Data Index: 738687 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.3440. Min Act: 0.0001

Data Index: 953995 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.2329. Min Act: -0.0000

Data Index: 600700 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.2298. Min Act: 0.0001

Data Index: 207427 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1895. Min Act: 0.0000

Data Index: 627570 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1812. Min Act: 0.0001

Data Index: 165159 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1968. Min Act: -0.0000

Data Index: 131279 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1221546 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1347. Min Act: 0.0000

Data Index: 1233364 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1233. Min Act: -0.0000

Data Index: 251720 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1171. Min Act: 0.0002

Data Index: 115124 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.1153. Min Act: 0.0000

Data Index: 1185720 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.0341. Min Act: 0.0002

Data Index: 273176 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.0256. Min Act: 0.0000

Data Index: 293337 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.0579. Min Act: -0.0000

Data Index: 158853 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 2.0195. Min Range: -2.0195

Max Act: 1.0565. Min Act: 0.0001

Data Index: 852670 (C4 (Web Text))

Max Activating Token Index: 590