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

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

Neuron 567 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.6501. Min Act: -0.0001

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.1604. Min Act: -0.0001

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.1443. Min Act: -0.0001

Data Index: 823401 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.5293. Min Act: -0.0001

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.0355. Min Act: -0.0001

Data Index: 816296 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.9079. Min Act: -0.0001

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.0143. Min Act: -0.0001

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.9795. Min Act: -0.0001

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.0444. Min Act: -0.0001

Data Index: 573030 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.9001. Min Act: -0.0001

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.8433. Min Act: -0.0001

Data Index: 994886 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.5295. Min Act: -0.0001

Data Index: 972176 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 5.6501. Min Range: -5.6501

Max Act: 4.1382. Min Act: -0.0001

Data Index: 949726 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.8992. Min Act: -0.0001

Data Index: 889146 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.2757. Min Act: -0.0001

Data Index: 1217145 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.6626. Min Act: -0.0001

Data Index: 1232839 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.3419. Min Act: -0.0001

Data Index: 1324748 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.6631. Min Act: -0.0001

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.9220. Min Act: -0.0001

Data Index: 591409 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 5.6501. Min Range: -5.6501

Max Act: 3.7194. Min Act: -0.0001

Data Index: 1296963 (C4 (Web Text))

Max Activating Token Index: 40