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

Dataset: The Pile

Neuron 4764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.4762. Min Act: -0.0000

Data Index: 463145 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2936. Min Act: -0.0000

Data Index: 359834 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1866060 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2828. Min Act: -0.0000

Data Index: 340733 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1657777 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1886784 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2546. Min Act: -0.0000

Data Index: 268129 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1438765 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2482. Min Act: -0.0000

Data Index: 398654 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2307. Min Act: -0.0000

Data Index: 940777 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1187160 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1132733 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2090. Min Act: -0.0000

Data Index: 729746 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1845447 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1832666 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2333. Min Act: -0.0000

Data Index: 403352 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2356. Min Act: -0.0000

Data Index: 942547 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1760775 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2225. Min Act: -0.0000

Data Index: 254534 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1602390 (The Pile)

Max Activating Token Index: 960