Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1186304 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1714. Min Act: -0.0000

Data Index: 34036 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1574. Min Act: -0.0001

Data Index: 552113 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1533. Min Act: -0.0000

Data Index: 161814 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1459. Min Act: -0.0000

Data Index: 448090 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1053848 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1379. Min Act: -0.0000

Data Index: 291998 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1398. Min Act: -0.0000

Data Index: 138067 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1487. Min Act: -0.0000

Data Index: 539432 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1215517 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1349. Min Act: -0.0001

Data Index: 319195 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1377. Min Act: -0.0001

Data Index: 978982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1038150 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1330. Min Act: -0.0001

Data Index: 965692 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1134556 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1103. Min Act: -0.0000

Data Index: 252480 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1261. Min Act: -0.0000

Data Index: 567168 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1173. Min Act: -0.0000

Data Index: 598940 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1253. Min Act: -0.0000

Data Index: 388743 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1211. Min Act: -0.0000

Data Index: 515469 (C4 (Web Text))

Max Activating Token Index: 564