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

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

Neuron 6103 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.1581. Min Range: -7.1581

Max Act: 7.1581. Min Act: -0.0000

Data Index: 876129 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 7.1581. Min Range: -7.1581

Max Act: 6.9781. Min Act: -0.0000

Data Index: 1058714 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 7.1581. Min Range: -7.1581

Max Act: 6.2800. Min Act: -0.0000

Data Index: 597097 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 7.1581. Min Range: -7.1581

Max Act: 5.9784. Min Act: -0.0000

Data Index: 939918 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 7.1581. Min Range: -7.1581

Max Act: 5.2465. Min Act: -0.0000

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 7.1581. Min Range: -7.1581

Max Act: 5.5287. Min Act: -0.0000

Data Index: 57305 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 7.1581. Min Range: -7.1581

Max Act: 5.0205. Min Act: -0.0000

Data Index: 958328 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.6405. Min Act: -0.0000

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.4111. Min Act: -0.0000

Data Index: 1318589 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.3496. Min Act: -0.0000

Data Index: 1054146 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.1375. Min Act: -0.0000

Data Index: 888483 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.1359. Min Act: -0.0000

Data Index: 539589 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.0239. Min Act: -0.0000

Data Index: 696307 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 7.1581. Min Range: -7.1581

Max Act: 4.0032. Min Act: -0.0000

Data Index: 190613 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.7209. Min Act: -0.0000

Data Index: 639820 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.8399. Min Act: -0.0000

Data Index: 622657 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.5720. Min Act: -0.0000

Data Index: 272276 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.5793. Min Act: -0.0000

Data Index: 77407 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.7313. Min Act: -0.0000

Data Index: 1203932 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 7.1581. Min Range: -7.1581

Max Act: 3.6340. Min Act: -0.0000

Data Index: 1079264 (C4 (Web Text))

Max Activating Token Index: 389