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

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

Neuron 595 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.6830. Min Act: -0.0000

Data Index: 235815 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4923. Min Act: -0.0000

Data Index: 831342 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4476. Min Act: -0.0000

Data Index: 915946 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4284. Min Act: -0.0000

Data Index: 354140 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4424. Min Act: -0.0000

Data Index: 891499 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1297210 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4380. Min Act: -0.0000

Data Index: 164976 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3739. Min Act: -0.0000

Data Index: 970848 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1265351 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1136892 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4167. Min Act: -0.0000

Data Index: 905307 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3775. Min Act: -0.0000

Data Index: 505010 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1284345 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3582. Min Act: -0.0000

Data Index: 140607 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3759. Min Act: -0.0000

Data Index: 714020 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3266. Min Act: -0.0000

Data Index: 743059 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3140. Min Act: -0.0000

Data Index: 831338 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3015. Min Act: -0.0000

Data Index: 954566 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3140. Min Act: -0.0000

Data Index: 583590 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.2588. Min Act: -0.0000

Data Index: 401531 (C4 (Web Text))

Max Activating Token Index: 886