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

Dataset: The Pile

Neuron 2323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1766547 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0868. Min Act: 0.0000

Data Index: 731365 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8189. Min Act: -0.0000

Data Index: 817663 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1222470 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0884. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9401. Min Act: -0.0000

Data Index: 852320 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0921. Min Act: -0.0000

Data Index: 108879 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0689. Min Act: -0.0000

Data Index: 28593 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1238052 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1907415 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9529. Min Act: -0.0000

Data Index: 731137 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1028932 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1082763 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9241. Min Act: -0.0000

Data Index: 924712 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9284. Min Act: -0.0000

Data Index: 577793 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7455. Min Act: 0.0001

Data Index: 1702119 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9118. Min Act: 0.0000

Data Index: 444446 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7904. Min Act: 0.0000

Data Index: 1737079 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1898606 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1497079 (The Pile)

Max Activating Token Index: 338