Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2859 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5843. Min Act: -0.0001

Data Index: 55944 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6356. Min Act: -0.0001

Data Index: 571287 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6260. Min Act: -0.0001

Data Index: 30952 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5818. Min Act: -0.0001

Data Index: 210286 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5833. Min Act: -0.0001

Data Index: 658739 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5609. Min Act: -0.0001

Data Index: 329936 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1009793 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5348. Min Act: -0.0001

Data Index: 838945 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5800. Min Act: -0.0001

Data Index: 1281220 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5573. Min Act: -0.0001

Data Index: 1248800 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6150. Min Act: -0.0001

Data Index: 931696 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5499. Min Act: -0.0001

Data Index: 1308900 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5418. Min Act: -0.0001

Data Index: 163435 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5175. Min Act: -0.0001

Data Index: 701849 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5508. Min Act: -0.0001

Data Index: 89112 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5310. Min Act: -0.0001

Data Index: 876258 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5265. Min Act: -0.0001

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5274. Min Act: -0.0001

Data Index: 132599 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4980. Min Act: -0.0001

Data Index: 797919 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5272. Min Act: -0.0001

Data Index: 1100822 (C4 (Web Text))

Max Activating Token Index: 174