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

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

Neuron 4634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1623386 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0002

Data Index: 530351 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1274. Min Act: -0.0002

Data Index: 439609 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1254. Min Act: -0.0002

Data Index: 324362 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1243. Min Act: -0.0002

Data Index: 240342 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1230. Min Act: -0.0002

Data Index: 99782 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1216. Min Act: -0.0002

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1219. Min Act: -0.0002

Data Index: 398348 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1172. Min Act: -0.0002

Data Index: 175012 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1202. Min Act: -0.0002

Data Index: 1382097 (Python Code)

Max Activating Token Index: 296

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1139. Min Act: -0.0002

Data Index: 230653 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1134. Min Act: -0.0002

Data Index: 599651 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1111. Min Act: -0.0002

Data Index: 579656 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1093. Min Act: -0.0002

Data Index: 564979 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1415063 (Python Code)

Max Activating Token Index: 898

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1031. Min Act: -0.0002

Data Index: 21003 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0954. Min Act: -0.0002

Data Index: 993270 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1412768 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0881. Min Act: -0.0002

Data Index: 362420 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0923. Min Act: -0.0002

Data Index: 519638 (C4 (Web Text))

Max Activating Token Index: 151