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

Dataset: The Pile

Neuron 1785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.7030. Min Range: -11.7030

Max Act: 11.7030. Min Act: -0.0000

Data Index: 1402331 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 11.7030. Min Range: -11.7030

Max Act: 11.1005. Min Act: -0.0000

Data Index: 1836238 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 11.7030. Min Range: -11.7030

Max Act: 10.5822. Min Act: 0.0000

Data Index: 187956 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 11.7030. Min Range: -11.7030

Max Act: 8.6648. Min Act: -0.0000

Data Index: 1208681 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 11.7030. Min Range: -11.7030

Max Act: 8.4010. Min Act: -0.0000

Data Index: 1845772 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.7282. Min Act: -0.0000

Data Index: 1097068 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.4742. Min Act: -0.0000

Data Index: 1092405 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.0548. Min Act: -0.0000

Data Index: 274728 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.2132. Min Act: 0.0000

Data Index: 506411 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.5356. Min Act: -0.0000

Data Index: 907800 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.2794. Min Act: -0.0000

Data Index: 70350 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.2833. Min Act: -0.0000

Data Index: 745405 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.6041. Min Act: -0.0000

Data Index: 191890 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.2723. Min Act: -0.0000

Data Index: 1688064 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.7531. Min Act: -0.0000

Data Index: 571282 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.5354. Min Act: 0.0000

Data Index: 777718 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.8243. Min Act: 0.0000

Data Index: 942337 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.3573. Min Act: 0.0000

Data Index: 1931402 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 11.7030. Min Range: -11.7030

Max Act: 7.4141. Min Act: -0.0000

Data Index: 29033 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 11.7030. Min Range: -11.7030

Max Act: 6.8729. Min Act: -0.0000

Data Index: 1638801 (The Pile)

Max Activating Token Index: 60