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

Dataset: The Pile

Neuron 3310 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: 4.4300. Min Range: -4.4300

Max Act: 4.4300. Min Act: -0.0000

Data Index: 907039 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.1206. Min Act: -0.0000

Data Index: 988321 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.8375. Min Act: -0.0000

Data Index: 1197417 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.9608. Min Act: -0.0000

Data Index: 394700 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.1466. Min Act: -0.0000

Data Index: 1100866 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.9128. Min Act: 0.0000

Data Index: 1222519 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7649. Min Act: -0.0000

Data Index: 48481 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.9202. Min Act: -0.0000

Data Index: 74051 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7706. Min Act: -0.0000

Data Index: 400120 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.6613. Min Act: 0.0000

Data Index: 84529 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.5758. Min Act: -0.0000

Data Index: 1684426 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.5183. Min Act: -0.0000

Data Index: 462615 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.4053. Min Act: 0.0000

Data Index: 1263727 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.5511. Min Act: -0.0000

Data Index: 241406 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.2335. Min Act: -0.0000

Data Index: 109516 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.3127. Min Act: -0.0000

Data Index: 1848350 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.1575. Min Act: -0.0000

Data Index: 1513459 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.1676. Min Act: -0.0000

Data Index: 215196 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.1846. Min Act: -0.0000

Data Index: 1427914 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.1204. Min Act: -0.0000

Data Index: 970877 (The Pile)

Max Activating Token Index: 942