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

Dataset: The Pile

Neuron 4094 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: 9.8304. Min Range: -9.8304

Max Act: 9.4142. Min Act: -0.0000

Data Index: 1174660 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 9.8304. Min Range: -9.8304

Max Act: 9.7773. Min Act: -0.0000

Data Index: 689962 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 9.8304. Min Range: -9.8304

Max Act: 4.7987. Min Act: -0.0000

Data Index: 1524209 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 9.8304. Min Range: -9.8304

Max Act: 9.8304. Min Act: -0.0000

Data Index: 938322 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 9.8304. Min Range: -9.8304

Max Act: 8.1280. Min Act: -0.0000

Data Index: 377185 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 9.8304. Min Range: -9.8304

Max Act: 7.1599. Min Act: -0.0000

Data Index: 931566 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 9.8304. Min Range: -9.8304

Max Act: 8.8858. Min Act: -0.0000

Data Index: 838385 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 9.8304. Min Range: -9.8304

Max Act: 8.5649. Min Act: -0.0000

Data Index: 1697265 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 9.8304. Min Range: -9.8304

Max Act: 7.2100. Min Act: -0.0000

Data Index: 1935101 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 9.8304. Min Range: -9.8304

Max Act: 7.1743. Min Act: -0.0000

Data Index: 1454210 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 9.8304. Min Range: -9.8304

Max Act: 6.3719. Min Act: -0.0000

Data Index: 775131 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 9.8304. Min Range: -9.8304

Max Act: 6.2789. Min Act: -0.0000

Data Index: 723612 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 9.8304. Min Range: -9.8304

Max Act: 6.8130. Min Act: -0.0000

Data Index: 1373918 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 9.8304. Min Range: -9.8304

Max Act: 5.5203. Min Act: -0.0000

Data Index: 1889868 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 9.8304. Min Range: -9.8304

Max Act: 8.9661. Min Act: -0.0000

Data Index: 1849972 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 9.8304. Min Range: -9.8304

Max Act: 5.9611. Min Act: -0.0000

Data Index: 514296 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 9.8304. Min Range: -9.8304

Max Act: 6.6865. Min Act: -0.0000

Data Index: 550307 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 9.8304. Min Range: -9.8304

Max Act: 4.5949. Min Act: -0.0000

Data Index: 1443721 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 9.8304. Min Range: -9.8304

Max Act: 4.0602. Min Act: -0.0000

Data Index: 1061118 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 9.8304. Min Range: -9.8304

Max Act: 6.9897. Min Act: 0.0000

Data Index: 1764112 (The Pile)

Max Activating Token Index: 989