Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 835 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0004

Data Index: 243292 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1041789 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0293. Min Act: -0.0004

Data Index: 478891 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0285. Min Act: -0.0004

Data Index: 951329 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1092699 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0004

Data Index: 831669 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0290. Min Act: -0.0004

Data Index: 173427 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0005

Data Index: 1112571 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0281. Min Act: -0.0004

Data Index: 809669 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0280. Min Act: -0.0005

Data Index: 273193 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0004

Data Index: 67935 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0005

Data Index: 886573 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0282. Min Act: -0.0004

Data Index: 94695 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1354422 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0275. Min Act: -0.0004

Data Index: 584359 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0005

Data Index: 97560 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0266. Min Act: -0.0004

Data Index: 151298 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0004

Data Index: 153767 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0269. Min Act: -0.0004

Data Index: 468329 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0274. Min Act: -0.0005

Data Index: 671224 (C4 (Web Text))

Max Activating Token Index: 190