Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1894. Min Range: -2.1894

Max Act: 2.1894. Min Act: -0.0000

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.6756. Min Act: -0.0000

Data Index: 32114 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1324430 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.4913. Min Act: -0.0000

Data Index: 227030 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.4469. Min Act: -0.0000

Data Index: 261028 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.3488. Min Act: -0.0000

Data Index: 438621 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.3333. Min Act: -0.0000

Data Index: 152216 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1127760 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.3513. Min Act: -0.0000

Data Index: 1061107 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2722. Min Act: -0.0000

Data Index: 4432 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2470. Min Act: -0.0000

Data Index: 75401 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1059362 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1093728 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2553. Min Act: -0.0000

Data Index: 99825 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2484. Min Act: -0.0001

Data Index: 443042 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1312438 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2319. Min Act: -0.0000

Data Index: 150390 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.1516. Min Act: -0.0000

Data Index: 160895 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1229511 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.1894. Min Range: -2.1894

Max Act: 1.3103. Min Act: -0.0000

Data Index: 498657 (C4 (Web Text))

Max Activating Token Index: 732