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

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

Neuron 4827 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: 0.6518. Min Range: -0.6518

Max Act: 0.6518. Min Act: -0.0000

Data Index: 552019 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5516. Min Act: -0.0000

Data Index: 139347 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5295. Min Act: -0.0000

Data Index: 693748 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5451. Min Act: -0.0000

Data Index: 807692 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5439. Min Act: -0.0000

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4994. Min Act: -0.0000

Data Index: 465252 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4803. Min Act: -0.0000

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4687. Min Act: -0.0000

Data Index: 773210 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5119. Min Act: -0.0000

Data Index: 974776 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4365. Min Act: -0.0000

Data Index: 970387 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1086875 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4181. Min Act: -0.0000

Data Index: 715562 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4274. Min Act: -0.0000

Data Index: 801333 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4028. Min Act: -0.0000

Data Index: 433029 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4008. Min Act: -0.0000

Data Index: 250857 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4093. Min Act: -0.0000

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 610