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

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

Neuron 3223 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: 1.0307. Min Range: -1.0307

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1006335 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.9175. Min Act: -0.0000

Data Index: 43930 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.9015. Min Act: -0.0000

Data Index: 189969 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8736. Min Act: -0.0000

Data Index: 237253 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8527. Min Act: -0.0000

Data Index: 773913 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7571. Min Act: -0.0000

Data Index: 444905 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7193. Min Act: -0.0000

Data Index: 33226 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6876. Min Act: -0.0000

Data Index: 821614 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6873. Min Act: -0.0000

Data Index: 143861 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6834. Min Act: -0.0000

Data Index: 565941 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1124659 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7166. Min Act: -0.0000

Data Index: 762748 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6517. Min Act: -0.0000

Data Index: 517415 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6442. Min Act: -0.0000

Data Index: 292394 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1114136 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1203374 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.5993. Min Act: -0.0000

Data Index: 351374 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.5630. Min Act: -0.0000

Data Index: 704799 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.6235. Min Act: -0.0000

Data Index: 431560 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.5678. Min Act: -0.0000

Data Index: 453918 (C4 (Web Text))

Max Activating Token Index: 799