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

Dataset: The Pile

Neuron 4017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5929. Min Act: -0.0000

Data Index: 190853 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.2537. Min Act: -0.0000

Data Index: 272896 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.9977. Min Act: -0.0000

Data Index: 137079 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1686342 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8980. Min Act: -0.0001

Data Index: 288098 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.7286. Min Act: -0.0000

Data Index: 431443 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.5579. Min Act: -0.0000

Data Index: 320212 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.6105. Min Act: -0.0000

Data Index: 167802 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3229. Min Act: -0.0000

Data Index: 1876369 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.5302. Min Act: -0.0000

Data Index: 365434 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.6350. Min Act: -0.0000

Data Index: 1483942 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3779. Min Act: -0.0000

Data Index: 938891 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3795. Min Act: -0.0000

Data Index: 1160098 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4765. Min Act: -0.0000

Data Index: 699061 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3392. Min Act: -0.0000

Data Index: 148621 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4382. Min Act: -0.0000

Data Index: 620804 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3083. Min Act: -0.0000

Data Index: 1318308 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4423. Min Act: -0.0000

Data Index: 20179 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4383. Min Act: -0.0000

Data Index: 59391 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4311. Min Act: -0.0000

Data Index: 775556 (The Pile)

Max Activating Token Index: 968