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

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

Neuron 1961 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0828. Min Range: -2.0828

Max Act: 2.0828. Min Act: -0.0000

Data Index: 48243 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.9275. Min Act: -0.0000

Data Index: 216811 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.8975. Min Act: -0.0000

Data Index: 985025 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.3446. Min Act: -0.0000

Data Index: 625242 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.3366. Min Act: -0.0000

Data Index: 824239 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1315785 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1489. Min Act: -0.0000

Data Index: 743283 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1452. Min Act: -0.0000

Data Index: 546363 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.2368. Min Act: -0.0000

Data Index: 35343 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1017249 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1695. Min Act: -0.0000

Data Index: 673621 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1205. Min Act: -0.0000

Data Index: 977482 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1802. Min Act: -0.0000

Data Index: 83224 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1189331 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1485. Min Act: -0.0000

Data Index: 574399 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.2014. Min Act: -0.0000

Data Index: 996423 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.0627. Min Act: -0.0000

Data Index: 973719 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1230. Min Act: -0.0000

Data Index: 413886 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1203266 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 2.0828. Min Range: -2.0828

Max Act: 1.0745. Min Act: -0.0000

Data Index: 962507 (C4 (Web Text))

Max Activating Token Index: 798