Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8000. Min Act: -0.0000

Data Index: 1126221 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8168. Min Act: -0.0000

Data Index: 1210172 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1981487 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1709347 (The Pile)

Max Activating Token Index: 809

Text #4

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8184. Min Act: -0.0000

Data Index: 1710692 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8442. Min Act: -0.0000

Data Index: 1298072 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7436. Min Act: -0.0000

Data Index: 288925 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1336436 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7106. Min Act: -0.0000

Data Index: 33742 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1144967 (The Pile)

Max Activating Token Index: 95

Text #10

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.5808. Min Act: -0.0000

Data Index: 175337 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7009. Min Act: -0.0000

Data Index: 1507523 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6935. Min Act: -0.0000

Data Index: 1250778 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1740945 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1548948 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6786. Min Act: -0.0000

Data Index: 170477 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6309. Min Act: -0.0000

Data Index: 607483 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6521. Min Act: -0.0000

Data Index: 1096683 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.7304. Min Act: -0.0000

Data Index: 1432534 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1200762 (The Pile)

Max Activating Token Index: 94