Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3886 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0630. Min Act: -0.0000

Data Index: 909919 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1745. Min Act: -0.0000

Data Index: 918023 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1346044 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0336. Min Act: -0.0000

Data Index: 431547 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9848. Min Act: -0.0000

Data Index: 794916 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1061400 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9381. Min Act: -0.0000

Data Index: 819140 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9409. Min Act: -0.0000

Data Index: 704337 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9065. Min Act: -0.0000

Data Index: 589273 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1202651 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9259. Min Act: -0.0000

Data Index: 882914 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9183. Min Act: -0.0000

Data Index: 26696 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1212236 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9019. Min Act: -0.0000

Data Index: 555611 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8162. Min Act: -0.0000

Data Index: 647379 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8949. Min Act: -0.0000

Data Index: 712514 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8247. Min Act: -0.0000

Data Index: 842657 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1284905 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8632. Min Act: -0.0000

Data Index: 836752 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8303. Min Act: -0.0000

Data Index: 349618 (C4 (Web Text))

Max Activating Token Index: 410