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

Dataset: The Pile

Neuron 2086 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.3009. Min Act: 0.0001

Data Index: 1657210 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.8171. Min Act: -0.0000

Data Index: 1836236 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.9061. Min Act: -0.0000

Data Index: 540127 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.7970. Min Act: -0.0000

Data Index: 423136 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.7385. Min Act: 0.0000

Data Index: 933379 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.4687. Min Act: -0.0000

Data Index: 986133 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.6315. Min Act: -0.0000

Data Index: 1227319 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.5774. Min Act: -0.0000

Data Index: 1719335 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.3195. Min Act: -0.0000

Data Index: 956855 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.3103. Min Act: -0.0000

Data Index: 1473471 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.3955. Min Act: -0.0000

Data Index: 374584 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1972710 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1968845 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.4719. Min Act: -0.0000

Data Index: 335072 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.1272. Min Act: -0.0000

Data Index: 262048 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1792406 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.0882. Min Act: -0.0000

Data Index: 1881021 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.3371. Min Act: -0.0000

Data Index: 1753821 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.0499. Min Act: -0.0000

Data Index: 682380 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 3.3009. Min Range: -3.3009

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1443101 (The Pile)

Max Activating Token Index: 478