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

Dataset: The Pile

Neuron 1376 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0000

Data Index: 243521 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1540323 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0464. Min Act: -0.0000

Data Index: 394628 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1202665 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1835563 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0426. Min Act: -0.0000

Data Index: 774372 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1471104 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1670771 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0407. Min Act: -0.0000

Data Index: 748218 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0415. Min Act: -0.0000

Data Index: 847331 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1636516 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1169128 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0351. Min Act: -0.0000

Data Index: 444148 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1987446 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0393. Min Act: -0.0000

Data Index: 883311 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0376. Min Act: -0.0000

Data Index: 774349 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1420822 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0360. Min Act: -0.0000

Data Index: 692693 (The Pile)

Max Activating Token Index: 947

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1354947 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0404. Min Act: -0.0000

Data Index: 666374 (The Pile)

Max Activating Token Index: 105