Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2322 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4961. Min Act: -0.0000

Data Index: 686494 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4573. Min Act: -0.0001

Data Index: 1912228 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4593. Min Act: 0.0000

Data Index: 1533575 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4649. Min Act: -0.0000

Data Index: 569796 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1297019 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3944. Min Act: -0.0000

Data Index: 670177 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3908. Min Act: -0.0000

Data Index: 652456 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4291. Min Act: -0.0000

Data Index: 537525 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1872749 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1952769 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3766. Min Act: -0.0000

Data Index: 99442 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1718832 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1089222 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1102257 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3129. Min Act: -0.0000

Data Index: 637874 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3406. Min Act: -0.0000

Data Index: 496883 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3401. Min Act: -0.0000

Data Index: 777694 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1933761 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3204. Min Act: -0.0001

Data Index: 714314 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3302. Min Act: -0.0000

Data Index: 179659 (The Pile)

Max Activating Token Index: 533