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

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

Neuron 3251 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: 1.2423. Min Range: -1.2423

Max Act: 1.1452. Min Act: -0.0001

Data Index: 373107 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.2423. Min Act: -0.0001

Data Index: 1229390 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.1996. Min Act: -0.0001

Data Index: 446549 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.2089. Min Act: -0.0001

Data Index: 449331 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.1067. Min Act: -0.0001

Data Index: 847074 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0982. Min Act: -0.0001

Data Index: 508743 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0250. Min Act: -0.0001

Data Index: 250230 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9627. Min Act: -0.0001

Data Index: 563907 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9696. Min Act: -0.0001

Data Index: 483888 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0119. Min Act: -0.0001

Data Index: 60599 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9894. Min Act: -0.0001

Data Index: 672184 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0141. Min Act: -0.0001

Data Index: 865557 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9794. Min Act: -0.0001

Data Index: 1159022 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9834. Min Act: -0.0001

Data Index: 677280 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9730. Min Act: -0.0001

Data Index: 305214 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0459. Min Act: -0.0001

Data Index: 887897 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9699. Min Act: -0.0001

Data Index: 702558 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1179102 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1088848 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1348839 (C4 (Web Text))

Max Activating Token Index: 366