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

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

Neuron 2159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9136. Min Act: -0.0003

Data Index: 1418923 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7578. Min Act: -0.0003

Data Index: 1414780 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8257. Min Act: -0.0003

Data Index: 1560080 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7114. Min Act: -0.0003

Data Index: 1637647 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9694. Min Act: -0.0003

Data Index: 1488635 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7709. Min Act: -0.0004

Data Index: 1585580 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6581. Min Act: -0.0003

Data Index: 1413836 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6828. Min Act: -0.0003

Data Index: 1381097 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7615. Min Act: -0.0003

Data Index: 1512291 (Python Code)

Max Activating Token Index: 246

Text #9

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6951. Min Act: -0.0003

Data Index: 1626889 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7582. Min Act: -0.0004

Data Index: 1556042 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8232. Min Act: -0.0003

Data Index: 1488201 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7065. Min Act: -0.0003

Data Index: 1399387 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6833. Min Act: -0.0003

Data Index: 1379262 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7044. Min Act: -0.0003

Data Index: 1478065 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6156. Min Act: -0.0003

Data Index: 1441576 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7839. Min Act: -0.0003

Data Index: 1614114 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7345. Min Act: -0.0003

Data Index: 1444460 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7553. Min Act: -0.0003

Data Index: 1656779 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6711. Min Act: -0.0003

Data Index: 1637459 (Python Code)

Max Activating Token Index: 396