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

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

Neuron 2268 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0001

Data Index: 233686 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1411. Min Act: -0.0001

Data Index: 418033 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1124506 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1093525 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1340601 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1314. Min Act: -0.0001

Data Index: 119756 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1273. Min Act: -0.0001

Data Index: 264445 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1066073 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1300. Min Act: -0.0001

Data Index: 733600 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1396. Min Act: -0.0001

Data Index: 905482 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1317. Min Act: -0.0001

Data Index: 513239 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1243634 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1036001 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1225. Min Act: -0.0001

Data Index: 949182 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1244. Min Act: -0.0001

Data Index: 947542 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1051741 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1290. Min Act: -0.0001

Data Index: 607902 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1213251 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1280. Min Act: -0.0001

Data Index: 985259 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1069589 (C4 (Web Text))

Max Activating Token Index: 596