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

Dataset: The Pile

Neuron 3245 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: 1.4814. Min Range: -1.4814

Max Act: 1.4814. Min Act: -0.0000

Data Index: 469182 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1257104 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2905. Min Act: -0.0000

Data Index: 875973 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.4367. Min Act: -0.0000

Data Index: 264645 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1062890 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1181072 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.3348. Min Act: -0.0000

Data Index: 283788 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1065979 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1941578 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2647. Min Act: -0.0000

Data Index: 307499 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1116318 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1754021 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2374. Min Act: -0.0000

Data Index: 153802 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2426. Min Act: -0.0000

Data Index: 922955 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1361. Min Act: -0.0000

Data Index: 78027 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1435600 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1364. Min Act: -0.0000

Data Index: 993616 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1646459 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1844. Min Act: -0.0000

Data Index: 326552 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1099. Min Act: -0.0000

Data Index: 226781 (The Pile)

Max Activating Token Index: 343