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

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

Neuron 5174 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0307. Min Range: -3.0307

Max Act: 3.0307. Min Act: -0.0000

Data Index: 1245295 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.9090. Min Act: -0.0000

Data Index: 23347 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 3.0307. Min Range: -3.0307

Max Act: 3.0273. Min Act: -0.0000

Data Index: 452506 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7985. Min Act: -0.0000

Data Index: 1074871 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7694. Min Act: -0.0000

Data Index: 257633 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1285252 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7891. Min Act: -0.0000

Data Index: 888073 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.9839. Min Act: -0.0000

Data Index: 1295995 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.4304. Min Act: -0.0000

Data Index: 157403 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1178500 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7789. Min Act: -0.0000

Data Index: 1257527 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7263. Min Act: -0.0000

Data Index: 1346412 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7069. Min Act: -0.0000

Data Index: 1160854 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.5861. Min Act: -0.0000

Data Index: 566095 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.5237. Min Act: -0.0000

Data Index: 400469 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.4541. Min Act: -0.0000

Data Index: 989022 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.7920. Min Act: -0.0000

Data Index: 677407 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.3178. Min Act: -0.0000

Data Index: 860178 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.4565. Min Act: -0.0000

Data Index: 715353 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 3.0307. Min Range: -3.0307

Max Act: 2.6186. Min Act: -0.0000

Data Index: 924785 (C4 (Web Text))

Max Activating Token Index: 520