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

Dataset: The Pile

Neuron 1521 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1944053 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3064. Min Act: -0.0000

Data Index: 735577 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3472. Min Act: -0.0000

Data Index: 146126 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1120485 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9514. Min Act: -0.0000

Data Index: 311365 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9421. Min Act: -0.0000

Data Index: 745617 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9370. Min Act: -0.0000

Data Index: 746603 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8810. Min Act: -0.0000

Data Index: 935960 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1943442 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8031. Min Act: -0.0000

Data Index: 843693 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1992716 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8394. Min Act: -0.0000

Data Index: 595156 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7152. Min Act: -0.0000

Data Index: 977899 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1294658 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7562. Min Act: -0.0000

Data Index: 261663 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1541196 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7197. Min Act: -0.0000

Data Index: 399366 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1316864 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7041. Min Act: -0.0000

Data Index: 686920 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7720. Min Act: -0.0000

Data Index: 354306 (The Pile)

Max Activating Token Index: 140