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

Dataset: The Pile

Neuron 4138 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: 3.2302. Min Range: -3.2302

Max Act: 2.9495. Min Act: -0.0000

Data Index: 1317896 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1034. Min Act: -0.0000

Data Index: 309165 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.2302. Min Act: -0.0000

Data Index: 1720960 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0597. Min Act: -0.0000

Data Index: 467951 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1758. Min Act: -0.0000

Data Index: 222500 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9589. Min Act: -0.0000

Data Index: 1270916 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0581. Min Act: -0.0000

Data Index: 480778 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.3591. Min Act: -0.0000

Data Index: 1693604 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9958. Min Act: -0.0000

Data Index: 1218859 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.8589. Min Act: -0.0000

Data Index: 1269024 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9899. Min Act: -0.0000

Data Index: 1526556 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9422. Min Act: -0.0000

Data Index: 398962 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9528. Min Act: -0.0000

Data Index: 1952744 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.7989. Min Act: -0.0000

Data Index: 572316 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.7631. Min Act: -0.0000

Data Index: 643894 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.6407. Min Act: -0.0000

Data Index: 1783054 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9514. Min Act: -0.0000

Data Index: 106511 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.8196. Min Act: -0.0000

Data Index: 1136617 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.9511. Min Act: -0.0000

Data Index: 214204 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 3.2302. Min Range: -3.2302

Max Act: 2.6856. Min Act: -0.0000

Data Index: 1197320 (The Pile)

Max Activating Token Index: 162