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

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

Neuron 1845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.7009. Min Act: 0.0000

Data Index: 579067 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.7124. Min Act: -0.0000

Data Index: 33312 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1431063 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1629539 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1218781 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6401. Min Act: -0.0000

Data Index: 851751 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1611485 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6759. Min Act: -0.0000

Data Index: 566769 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6404. Min Act: -0.0000

Data Index: 978959 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6467. Min Act: -0.0000

Data Index: 809948 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6872. Min Act: -0.0000

Data Index: 697459 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1532226 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6374. Min Act: -0.0000

Data Index: 709142 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1427020 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1375250 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1522502 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1370588 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1279414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1618455 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6057. Min Act: -0.0000

Data Index: 178024 (C4 (Web Text))

Max Activating Token Index: 968