Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0003

Data Index: 552621 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0313. Min Act: -0.0003

Data Index: 400187 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0288. Min Act: -0.0003

Data Index: 756931 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1380884 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0003

Data Index: 845460 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1313857 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0261. Min Act: -0.0003

Data Index: 885260 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0266. Min Act: -0.0003

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0251. Min Act: -0.0004

Data Index: 1449322 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0260. Min Act: -0.0003

Data Index: 200744 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1051722 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0250. Min Act: -0.0003

Data Index: 669909 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1007499 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1231217 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0257. Min Act: -0.0003

Data Index: 522376 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0234. Min Act: -0.0003

Data Index: 100455 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0250. Min Act: -0.0003

Data Index: 326709 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0249. Min Act: -0.0003

Data Index: 330917 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0003

Data Index: 332721 (C4 (Web Text))

Max Activating Token Index: 632