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

Dataset: The Pile

Neuron 3339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3625. Min Range: -1.3625

Max Act: 1.3625. Min Act: 0.0000

Data Index: 776101 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 1.3625. Min Range: -1.3625

Max Act: 1.0533. Min Act: -0.0000

Data Index: 312488 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 1.3625. Min Range: -1.3625

Max Act: 1.0239. Min Act: -0.0000

Data Index: 686653 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1690426 (The Pile)

Max Activating Token Index: 479

Text #4

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1130170 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1650971 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1878100 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1245181 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8734. Min Act: -0.0000

Data Index: 55008 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1070799 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8090. Min Act: -0.0000

Data Index: 140189 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8023. Min Act: 0.0000

Data Index: 894394 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1359720 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1275885 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7529. Min Act: 0.0000

Data Index: 1145752 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1450178 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1199858 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7589. Min Act: 0.0000

Data Index: 1083817 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1739770 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 1.3625. Min Range: -1.3625

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1874238 (The Pile)

Max Activating Token Index: 650