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

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

Neuron 2123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8451. Min Range: -2.8451

Max Act: 2.8451. Min Act: -0.0000

Data Index: 304379 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.8451. Min Range: -2.8451

Max Act: 2.6195. Min Act: 0.0000

Data Index: 448798 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 2.8451. Min Range: -2.8451

Max Act: 2.2336. Min Act: 0.0000

Data Index: 789010 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.8451. Min Range: -2.8451

Max Act: 2.1287. Min Act: -0.0001

Data Index: 494878 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 2.8451. Min Range: -2.8451

Max Act: 2.0908. Min Act: 0.0000

Data Index: 251222 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.9636. Min Act: 0.0000

Data Index: 876765 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.6342. Min Act: -0.0000

Data Index: 399562 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.9165. Min Act: -0.0000

Data Index: 984970 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.8977. Min Act: -0.0000

Data Index: 745270 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.7916. Min Act: 0.0000

Data Index: 429933 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.6730. Min Act: -0.0001

Data Index: 1121738 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.7183. Min Act: -0.0000

Data Index: 352184 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.5496. Min Act: -0.0000

Data Index: 452978 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.4114. Min Act: 0.0000

Data Index: 946752 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.5871. Min Act: 0.0000

Data Index: 1068601 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.4463. Min Act: -0.0001

Data Index: 266696 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1269251 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.4292. Min Act: -0.0000

Data Index: 570756 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.5774. Min Act: -0.0001

Data Index: 662248 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 2.8451. Min Range: -2.8451

Max Act: 1.4383. Min Act: 0.0000

Data Index: 936925 (C4 (Web Text))

Max Activating Token Index: 623