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

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

Neuron 63 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6272. Min Range: -2.6272

Max Act: 2.6272. Min Act: -0.0000

Data Index: 877961 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.6272. Min Range: -2.6272

Max Act: 2.3717. Min Act: -0.0000

Data Index: 445209 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.6272. Min Range: -2.6272

Max Act: 2.0781. Min Act: -0.0000

Data Index: 1197115 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.9341. Min Act: -0.0000

Data Index: 313986 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.9205. Min Act: -0.0000

Data Index: 530761 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.8065. Min Act: -0.0000

Data Index: 89716 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.6272. Min Range: -2.6272

Max Act: 2.0020. Min Act: -0.0000

Data Index: 963335 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 2.6272. Min Range: -2.6272

Max Act: 2.0292. Min Act: -0.0000

Data Index: 991101 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.9206. Min Act: -0.0000

Data Index: 1294952 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.8537. Min Act: -0.0000

Data Index: 611604 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.8542. Min Act: -0.0000

Data Index: 560716 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.8834. Min Act: -0.0000

Data Index: 129209 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.7286. Min Act: -0.0000

Data Index: 358451 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1075566 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.8025. Min Act: -0.0000

Data Index: 556450 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.4900. Min Act: -0.0000

Data Index: 164668 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.5666. Min Act: -0.0000

Data Index: 289996 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.6864. Min Act: -0.0000

Data Index: 839097 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.6272. Min Range: -2.6272

Max Act: 1.5875. Min Act: -0.0000

Data Index: 612251 (C4 (Web Text))

Max Activating Token Index: 655