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

Dataset: The Pile

Neuron 3090 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: 4.2620. Min Range: -4.2620

Max Act: 4.2620. Min Act: -0.0000

Data Index: 1906727 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.5899. Min Act: -0.0000

Data Index: 1344934 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.4419. Min Act: -0.0000

Data Index: 1053975 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.4769. Min Act: -0.0000

Data Index: 308622 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.3137. Min Act: -0.0000

Data Index: 952126 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.6320. Min Act: -0.0000

Data Index: 1007562 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.3276. Min Act: -0.0000

Data Index: 1903719 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.4421. Min Act: -0.0000

Data Index: 23850 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1268911 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.2256. Min Act: -0.0000

Data Index: 357656 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.3658. Min Act: -0.0000

Data Index: 248461 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.0232. Min Act: -0.0000

Data Index: 703357 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1955. Min Act: -0.0000

Data Index: 1150890 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1533. Min Act: -0.0000

Data Index: 1164000 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1308. Min Act: -0.0000

Data Index: 935606 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 4.2620. Min Range: -4.2620

Max Act: 2.9783. Min Act: -0.0000

Data Index: 1957150 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1161. Min Act: -0.0000

Data Index: 1815163 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1204. Min Act: -0.0000

Data Index: 1456465 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.2546. Min Act: -0.0000

Data Index: 1501960 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 4.2620. Min Range: -4.2620

Max Act: 3.1850. Min Act: -0.0000

Data Index: 427081 (The Pile)

Max Activating Token Index: 725