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

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

Neuron 4429 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: 0.9803. Min Range: -0.9803

Max Act: 0.9803. Min Act: -0.0000

Data Index: 330355 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8709. Min Act: -0.0000

Data Index: 915933 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8239. Min Act: -0.0000

Data Index: 25980 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1161089 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7386. Min Act: -0.0000

Data Index: 983246 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1254311 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1195945 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6698. Min Act: -0.0000

Data Index: 834350 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7779. Min Act: 0.0000

Data Index: 960979 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6959. Min Act: 0.0000

Data Index: 354241 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6915. Min Act: -0.0000

Data Index: 34186 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6548. Min Act: -0.0000

Data Index: 576661 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1344214 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6530. Min Act: -0.0000

Data Index: 530569 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1022178 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6009. Min Act: -0.0000

Data Index: 397119 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6445. Min Act: -0.0000

Data Index: 472022 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6008. Min Act: -0.0000

Data Index: 999737 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.5547. Min Act: -0.0000

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 271