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

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

Neuron 1846 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8633. Min Act: -0.0000

Data Index: 341373 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8714. Min Act: -0.0000

Data Index: 813575 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8406. Min Act: -0.0000

Data Index: 318124 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6954. Min Act: -0.0000

Data Index: 451858 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8316. Min Act: -0.0000

Data Index: 502442 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7550. Min Act: -0.0000

Data Index: 589930 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7328. Min Act: -0.0000

Data Index: 189378 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1036478 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7671. Min Act: -0.0000

Data Index: 430795 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1080488 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1244698 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6860. Min Act: -0.0000

Data Index: 848161 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6907. Min Act: -0.0000

Data Index: 193265 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6444. Min Act: -0.0000

Data Index: 170939 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6913. Min Act: -0.0000

Data Index: 150853 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6306. Min Act: -0.0000

Data Index: 301175 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6416. Min Act: -0.0000

Data Index: 851294 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1216453 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6576. Min Act: -0.0000

Data Index: 154598 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1177772 (C4 (Web Text))

Max Activating Token Index: 211