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

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

Neuron 4060 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6997. Min Range: -4.6997

Max Act: 4.6997. Min Act: -0.0000

Data Index: 374975 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 4.6997. Min Range: -4.6997

Max Act: 4.1848. Min Act: -0.0001

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.8495. Min Act: -0.0000

Data Index: 30793 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 4.6997. Min Range: -4.6997

Max Act: 4.0785. Min Act: -0.0000

Data Index: 128454 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.8699. Min Act: -0.0000

Data Index: 262573 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.6749. Min Act: -0.0000

Data Index: 139120 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 4.6997. Min Range: -4.6997

Max Act: 4.0652. Min Act: -0.0000

Data Index: 1343128 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 4.6997. Min Range: -4.6997

Max Act: 4.1997. Min Act: -0.0001

Data Index: 767813 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.7316. Min Act: -0.0000

Data Index: 1215430 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.7137. Min Act: -0.0000

Data Index: 1308267 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.3354. Min Act: -0.0000

Data Index: 137392 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.8428. Min Act: -0.0000

Data Index: 686892 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.8420. Min Act: -0.0000

Data Index: 1121257 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.5940. Min Act: -0.0000

Data Index: 97513 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.9521. Min Act: -0.0000

Data Index: 1349935 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.2405. Min Act: -0.0000

Data Index: 1049255 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.4870. Min Act: -0.0000

Data Index: 206060 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.2589. Min Act: -0.0000

Data Index: 2525 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.4947. Min Act: -0.0000

Data Index: 31660 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 4.6997. Min Range: -4.6997

Max Act: 3.6292. Min Act: -0.0000

Data Index: 712652 (C4 (Web Text))

Max Activating Token Index: 629