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

Dataset: The Pile

Neuron 191 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.5428. Min Act: -0.0000

Data Index: 618661 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.3272. Min Act: -0.0000

Data Index: 596493 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2904. Min Act: -0.0000

Data Index: 438371 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1979935 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2131. Min Act: -0.0000

Data Index: 795086 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1989166 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2819. Min Act: -0.0000

Data Index: 652311 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1444. Min Act: -0.0000

Data Index: 689815 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1372. Min Act: -0.0000

Data Index: 798032 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0242. Min Act: -0.0000

Data Index: 54853 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0880. Min Act: -0.0000

Data Index: 191877 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9488. Min Act: -0.0000

Data Index: 541001 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1512940 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1366424 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1473217 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0167. Min Act: -0.0000

Data Index: 515330 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.8950. Min Act: -0.0000

Data Index: 228251 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1426756 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1863531 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1349747 (The Pile)

Max Activating Token Index: 99