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

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

Neuron 4010 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: 0.7571. Min Range: -0.7571

Max Act: 0.7523. Min Act: -0.0001

Data Index: 1413971 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7016. Min Act: -0.0001

Data Index: 1649909 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1465935 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7560. Min Act: -0.0001

Data Index: 1504621 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6918. Min Act: -0.0001

Data Index: 1586813 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7114. Min Act: -0.0001

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6926. Min Act: -0.0001

Data Index: 1597088 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1416483 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1639931 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6229. Min Act: -0.0001

Data Index: 16840 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6540. Min Act: -0.0001

Data Index: 113935 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6139. Min Act: -0.0001

Data Index: 644167 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6483. Min Act: -0.0001

Data Index: 1157923 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6599. Min Act: -0.0001

Data Index: 973072 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1527349 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6409. Min Act: -0.0001

Data Index: 43072 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1033747 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6108. Min Act: -0.0001

Data Index: 1424388 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1018163 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6585. Min Act: -0.0001

Data Index: 162240 (C4 (Web Text))

Max Activating Token Index: 79