Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.1290. Min Act: -0.0001

Data Index: 421814 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.1259. Min Act: -0.0001

Data Index: 1052955 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9115. Min Act: -0.0001

Data Index: 1019143 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8961. Min Act: -0.0001

Data Index: 338076 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8314. Min Act: -0.0001

Data Index: 995420 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8828. Min Act: -0.0001

Data Index: 495375 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8355. Min Act: -0.0001

Data Index: 33283 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1223446 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8376. Min Act: -0.0001

Data Index: 270757 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8255. Min Act: -0.0001

Data Index: 1176459 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1003671 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8199. Min Act: -0.0001

Data Index: 9168 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.7920. Min Act: -0.0001

Data Index: 575778 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1157272 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8094. Min Act: -0.0001

Data Index: 654288 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.7845. Min Act: -0.0001

Data Index: 253639 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1320099 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8007. Min Act: -0.0001

Data Index: 84258 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.7726. Min Act: -0.0001

Data Index: 451897 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.7905. Min Act: -0.0001

Data Index: 176966 (C4 (Web Text))

Max Activating Token Index: 830