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

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

Neuron 470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4627. Min Range: -6.4627

Max Act: 6.4627. Min Act: -0.0001

Data Index: 530876 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 6.4627. Min Range: -6.4627

Max Act: 5.6243. Min Act: -0.0001

Data Index: 398509 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 6.4627. Min Range: -6.4627

Max Act: 5.7240. Min Act: -0.0000

Data Index: 345136 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 6.4627. Min Range: -6.4627

Max Act: 5.7240. Min Act: -0.0001

Data Index: 679570 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 6.4627. Min Range: -6.4627

Max Act: 5.0548. Min Act: -0.0001

Data Index: 415948 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.5189. Min Act: -0.0000

Data Index: 1246444 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.1959. Min Act: -0.0000

Data Index: 791739 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.5132. Min Act: -0.0001

Data Index: 1106663 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.3219. Min Act: -0.0000

Data Index: 1256763 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.1238. Min Act: -0.0001

Data Index: 1014570 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.3326. Min Act: -0.0000

Data Index: 920062 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.2506. Min Act: -0.0000

Data Index: 1109466 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.1992. Min Act: -0.0001

Data Index: 1004700 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.8643. Min Act: -0.0001

Data Index: 1052976 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.3883. Min Act: -0.0000

Data Index: 451236 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 6.4627. Min Range: -6.4627

Max Act: 4.1081. Min Act: -0.0001

Data Index: 949498 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.6367. Min Act: -0.0001

Data Index: 1129330 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.7578. Min Act: -0.0001

Data Index: 275371 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.7326. Min Act: -0.0001

Data Index: 466574 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 6.4627. Min Range: -6.4627

Max Act: 3.5408. Min Act: -0.0001

Data Index: 808329 (C4 (Web Text))

Max Activating Token Index: 711