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

Dataset: The Pile

Neuron 4688 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: 3.0574. Min Range: -3.0574

Max Act: 3.0574. Min Act: -0.0000

Data Index: 1334599 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.8467. Min Act: 0.0000

Data Index: 1126239 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.9445. Min Act: -0.0000

Data Index: 1506166 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.3942. Min Act: -0.0000

Data Index: 664459 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.5264. Min Act: -0.0000

Data Index: 1287380 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.4852. Min Act: -0.0000

Data Index: 805970 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.4342. Min Act: -0.0000

Data Index: 685978 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.4022. Min Act: -0.0000

Data Index: 1695257 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.2591. Min Act: -0.0000

Data Index: 147925 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.0842. Min Act: 0.0000

Data Index: 7236 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1513. Min Act: -0.0000

Data Index: 186900 (The Pile)

Max Activating Token Index: 584

Text #11

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1358. Min Act: -0.0000

Data Index: 985804 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1409. Min Act: -0.0000

Data Index: 951543 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1336273 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1078. Min Act: -0.0000

Data Index: 222757 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.1048. Min Act: -0.0000

Data Index: 102377 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 3.0574. Min Range: -3.0574

Max Act: 1.9897. Min Act: -0.0000

Data Index: 1469047 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 3.0574. Min Range: -3.0574

Max Act: 1.9782. Min Act: -0.0000

Data Index: 488605 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.0720. Min Act: -0.0000

Data Index: 926448 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 3.0574. Min Range: -3.0574

Max Act: 2.0882. Min Act: -0.0000

Data Index: 20606 (The Pile)

Max Activating Token Index: 209