Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 226 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0100. Min Act: -0.0001

Data Index: 306682 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0299. Min Act: -0.0000

Data Index: 226701 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9544. Min Act: -0.0001

Data Index: 699111 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9632. Min Act: -0.0001

Data Index: 691432 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9235. Min Act: -0.0002

Data Index: 634638 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8460. Min Act: -0.0001

Data Index: 1014706 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8612. Min Act: -0.0000

Data Index: 503422 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8236. Min Act: -0.0002

Data Index: 1069536 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1172678 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7778. Min Act: -0.0001

Data Index: 1014302 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1255664 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8159. Min Act: -0.0001

Data Index: 969912 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8199. Min Act: -0.0001

Data Index: 922462 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1177479 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7850. Min Act: -0.0001

Data Index: 703468 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8158. Min Act: -0.0002

Data Index: 184738 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7953. Min Act: -0.0001

Data Index: 251077 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7828. Min Act: -0.0002

Data Index: 812887 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1048297 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.7578. Min Act: -0.0001

Data Index: 389490 (C4 (Web Text))

Max Activating Token Index: 384