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

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

Neuron 5659 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0000

Data Index: 506292 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1241987 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1191275 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1185496 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1130508 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2066. Min Act: -0.0000

Data Index: 847856 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2044. Min Act: -0.0000

Data Index: 496325 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1208455 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2028. Min Act: 0.0000

Data Index: 764066 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1200217 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1320148 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1829. Min Act: -0.0000

Data Index: 724445 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1783. Min Act: -0.0000

Data Index: 671108 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1814. Min Act: -0.0000

Data Index: 752527 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1286800 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1722. Min Act: -0.0000

Data Index: 109686 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1072201 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1647. Min Act: -0.0000

Data Index: 496309 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1669. Min Act: -0.0000

Data Index: 236270 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1650. Min Act: 0.0000

Data Index: 209182 (C4 (Web Text))

Max Activating Token Index: 436