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

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

Neuron 3470 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: 8.2978. Min Range: -8.2978

Max Act: 8.2978. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 8.2978. Min Range: -8.2978

Max Act: 6.6215. Min Act: -0.0000

Data Index: 647920 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 8.2978. Min Range: -8.2978

Max Act: 5.9955. Min Act: -0.0000

Data Index: 811540 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 8.2978. Min Range: -8.2978

Max Act: 6.1323. Min Act: -0.0000

Data Index: 681349 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 8.2978. Min Range: -8.2978

Max Act: 7.4389. Min Act: -0.0000

Data Index: 961614 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 8.2978. Min Range: -8.2978

Max Act: 4.7692. Min Act: -0.0000

Data Index: 672175 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 8.2978. Min Range: -8.2978

Max Act: 6.1114. Min Act: -0.0000

Data Index: 1358852 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 8.2978. Min Range: -8.2978

Max Act: 5.2305. Min Act: -0.0000

Data Index: 627083 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 8.2978. Min Range: -8.2978

Max Act: 4.5529. Min Act: -0.0000

Data Index: 968201 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 8.2978. Min Range: -8.2978

Max Act: 4.6865. Min Act: -0.0000

Data Index: 436713 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 8.2978. Min Range: -8.2978

Max Act: 4.1467. Min Act: -0.0000

Data Index: 616589 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.3817. Min Act: -0.0000

Data Index: 640941 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.8590. Min Act: -0.0000

Data Index: 15365 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.9806. Min Act: -0.0000

Data Index: 487325 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.9431. Min Act: 0.0000

Data Index: 941165 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.9090. Min Act: 0.0000

Data Index: 1284066 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.9240. Min Act: -0.0000

Data Index: 1312011 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.4382. Min Act: -0.0000

Data Index: 810871 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.8205. Min Act: -0.0000

Data Index: 395394 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 8.2978. Min Range: -8.2978

Max Act: 3.6852. Min Act: 0.0000

Data Index: 1073179 (C4 (Web Text))

Max Activating Token Index: 23