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

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

Neuron 3776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5967. Min Range: -3.5967

Max Act: 3.5967. Min Act: -0.0001

Data Index: 584450 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 3.5967. Min Range: -3.5967

Max Act: 2.3525. Min Act: -0.0001

Data Index: 1241536 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.8640. Min Act: -0.0001

Data Index: 919684 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.5266. Min Act: -0.0001

Data Index: 252629 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.4225. Min Act: -0.0001

Data Index: 793442 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.6090. Min Act: -0.0001

Data Index: 963753 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1709. Min Act: -0.0001

Data Index: 290813 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.3318. Min Act: -0.0001

Data Index: 889613 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1339659 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1585. Min Act: -0.0001

Data Index: 909840 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.2101. Min Act: -0.0001

Data Index: 961378 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1633. Min Act: -0.0001

Data Index: 169603 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.2495. Min Act: -0.0001

Data Index: 271237 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1879. Min Act: -0.0001

Data Index: 1276036 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1632. Min Act: -0.0001

Data Index: 1328758 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1433. Min Act: -0.0001

Data Index: 467967 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.0541. Min Act: -0.0001

Data Index: 721375 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1718. Min Act: -0.0001

Data Index: 234574 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.0409. Min Act: -0.0001

Data Index: 796178 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 3.5967. Min Range: -3.5967

Max Act: 1.1051. Min Act: -0.0001

Data Index: 434978 (C4 (Web Text))

Max Activating Token Index: 231