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

Dataset: The Pile

Neuron 567 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1137232 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7337. Min Act: -0.0000

Data Index: 6850 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7337. Min Act: -0.0000

Data Index: 859141 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7394. Min Act: -0.0000

Data Index: 326974 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1111690 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1962917 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1184849 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8133. Min Act: -0.0000

Data Index: 991161 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1349587 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1470551 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1590768 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6515. Min Act: -0.0000

Data Index: 7225 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1224046 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1583927 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6897. Min Act: -0.0000

Data Index: 964926 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1870002 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1448519 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6859. Min Act: -0.0000

Data Index: 522615 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6444. Min Act: -0.0000

Data Index: 62747 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1696689 (The Pile)

Max Activating Token Index: 508