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

Dataset: The Pile

Neuron 3804 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: 0.3401. Min Range: -0.3401

Max Act: 0.3401. Min Act: -0.0000

Data Index: 980711 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1198337 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1239773 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1951500 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2571. Min Act: -0.0000

Data Index: 117356 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1947765 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1887806 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1319553 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2360. Min Act: -0.0000

Data Index: 562857 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1218563 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1696699 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1095556 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1912. Min Act: -0.0000

Data Index: 495442 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2039. Min Act: -0.0000

Data Index: 308750 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1999. Min Act: -0.0000

Data Index: 995157 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2006. Min Act: -0.0000

Data Index: 710143 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1529289 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1872. Min Act: -0.0000

Data Index: 315974 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1965. Min Act: -0.0000

Data Index: 772170 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1719398 (The Pile)

Max Activating Token Index: 345