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

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

Neuron 4439 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.3709. Min Act: -0.0001

Data Index: 246857 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2972. Min Act: -0.0001

Data Index: 1259676 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2777. Min Act: -0.0001

Data Index: 968304 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.3477. Min Act: -0.0001

Data Index: 616551 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2682. Min Act: -0.0001

Data Index: 357533 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2721. Min Act: -0.0001

Data Index: 972502 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2427. Min Act: -0.0001

Data Index: 971253 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2232. Min Act: -0.0001

Data Index: 1181240 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1799. Min Act: -0.0001

Data Index: 19385 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1227. Min Act: -0.0001

Data Index: 898806 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1705. Min Act: -0.0001

Data Index: 521673 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2433. Min Act: -0.0001

Data Index: 378204 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2061. Min Act: -0.0001

Data Index: 1191480 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0792. Min Act: -0.0001

Data Index: 1075261 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1381. Min Act: -0.0001

Data Index: 390030 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0972. Min Act: -0.0001

Data Index: 711203 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1952. Min Act: -0.0001

Data Index: 408263 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1633. Min Act: -0.0001

Data Index: 953087 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1557. Min Act: -0.0001

Data Index: 1115005 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.1497. Min Act: -0.0001

Data Index: 1030470 (C4 (Web Text))

Max Activating Token Index: 488