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

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

Neuron 128 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: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0000

Data Index: 798295 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0000

Data Index: 456807 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0243. Min Act: -0.0000

Data Index: 768392 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0230. Min Act: -0.0000

Data Index: 286747 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0000

Data Index: 655733 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1126374 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1124308 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0197. Min Act: -0.0000

Data Index: 983927 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0197. Min Act: -0.0000

Data Index: 819050 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0199. Min Act: -0.0000

Data Index: 81390 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0180. Min Act: -0.0000

Data Index: 52681 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0183. Min Act: -0.0000

Data Index: 1443418 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0176. Min Act: -0.0000

Data Index: 273964 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0158. Min Act: -0.0000

Data Index: 653380 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0183. Min Act: -0.0000

Data Index: 375640 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0179. Min Act: -0.0000

Data Index: 22135 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0174. Min Act: -0.0000

Data Index: 205327 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1062277 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0154. Min Act: -0.0000

Data Index: 688900 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0173. Min Act: -0.0000

Data Index: 246921 (C4 (Web Text))

Max Activating Token Index: 258