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

Dataset: The Pile

Neuron 3279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5854. Min Range: -5.5854

Max Act: 5.5854. Min Act: -0.0000

Data Index: 484104 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 5.5854. Min Range: -5.5854

Max Act: 5.3714. Min Act: -0.0000

Data Index: 831986 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 5.5854. Min Range: -5.5854

Max Act: 5.5614. Min Act: -0.0000

Data Index: 1882829 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 5.5854. Min Range: -5.5854

Max Act: 5.3996. Min Act: -0.0000

Data Index: 1900351 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 5.5854. Min Range: -5.5854

Max Act: 4.4922. Min Act: -0.0000

Data Index: 1119564 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 5.5854. Min Range: -5.5854

Max Act: 4.1152. Min Act: -0.0000

Data Index: 1470908 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.8694. Min Act: -0.0000

Data Index: 755183 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.7081. Min Act: -0.0000

Data Index: 778357 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.5395. Min Act: -0.0000

Data Index: 1273640 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.7952. Min Act: -0.0000

Data Index: 1917637 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.6269. Min Act: -0.0000

Data Index: 460016 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.7335. Min Act: -0.0000

Data Index: 1878859 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.6843. Min Act: -0.0000

Data Index: 1317312 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.3591. Min Act: -0.0000

Data Index: 97713 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.5057. Min Act: -0.0000

Data Index: 1266933 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.2533. Min Act: -0.0000

Data Index: 359897 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.2359. Min Act: -0.0000

Data Index: 1275388 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.2157. Min Act: -0.0000

Data Index: 43816 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.1996. Min Act: -0.0000

Data Index: 1820012 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 5.5854. Min Range: -5.5854

Max Act: 3.0325. Min Act: -0.0000

Data Index: 160693 (The Pile)

Max Activating Token Index: 978