Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.9883. Min Act: -0.0000

Data Index: 829659 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5703. Min Act: -0.0000

Data Index: 550014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1179069 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1250. Min Act: -0.0000

Data Index: 667601 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.2575. Min Act: -0.0000

Data Index: 351506 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1152632 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1361. Min Act: -0.0000

Data Index: 388679 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0285. Min Act: -0.0000

Data Index: 385908 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1719. Min Act: -0.0000

Data Index: 477157 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1166285 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1344. Min Act: -0.0000

Data Index: 260407 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1292. Min Act: -0.0001

Data Index: 846264 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0795. Min Act: -0.0000

Data Index: 820795 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0582. Min Act: -0.0001

Data Index: 731598 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.1319. Min Act: -0.0000

Data Index: 244947 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0540. Min Act: -0.0000

Data Index: 860803 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0278. Min Act: -0.0000

Data Index: 480649 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0235. Min Act: -0.0000

Data Index: 871004 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.0698. Min Act: -0.0000

Data Index: 196285 (C4 (Web Text))

Max Activating Token Index: 1002