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

Dataset: The Pile

Neuron 4328 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1483817 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1037114 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8620. Min Act: -0.0000

Data Index: 155503 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1120700 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1403202 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1470148 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1489403 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9107. Min Act: -0.0000

Data Index: 682540 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8873. Min Act: -0.0000

Data Index: 753808 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1209332 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8304. Min Act: -0.0000

Data Index: 207904 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8338. Min Act: -0.0000

Data Index: 773478 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7342. Min Act: -0.0000

Data Index: 192973 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7811. Min Act: -0.0000

Data Index: 812074 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7315. Min Act: -0.0000

Data Index: 705196 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1170163 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1676759 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8352. Min Act: -0.0000

Data Index: 30242 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.5733. Min Act: -0.0000

Data Index: 157627 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.7651. Min Act: -0.0000

Data Index: 105571 (The Pile)

Max Activating Token Index: 416