Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1032382 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.9812. Min Act: -0.0001

Data Index: 542820 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7700. Min Act: -0.0001

Data Index: 600178 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7205. Min Act: -0.0001

Data Index: 125028 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7938. Min Act: -0.0001

Data Index: 104790 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7889. Min Act: -0.0001

Data Index: 1022377 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7592. Min Act: -0.0001

Data Index: 907298 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7073. Min Act: -0.0001

Data Index: 377573 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1125056 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7543. Min Act: -0.0001

Data Index: 331275 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6871. Min Act: -0.0001

Data Index: 192234 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1238415 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6504. Min Act: -0.0001

Data Index: 974827 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1003042 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6555. Min Act: -0.0001

Data Index: 1080739 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6980. Min Act: -0.0001

Data Index: 1301473 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6159. Min Act: -0.0001

Data Index: 672778 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6760. Min Act: -0.0001

Data Index: 647291 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7519. Min Act: -0.0001

Data Index: 976212 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6924. Min Act: -0.0001

Data Index: 302424 (C4 (Web Text))

Max Activating Token Index: 383