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

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

Neuron 5000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6002. Min Act: -0.0000

Data Index: 248507 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6340. Min Act: -0.0000

Data Index: 403777 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6243. Min Act: -0.0000

Data Index: 662853 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6157. Min Act: -0.0000

Data Index: 373771 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.7059. Min Act: -0.0000

Data Index: 517836 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5076. Min Act: -0.0000

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5799. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5728. Min Act: -0.0000

Data Index: 1326428 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5676. Min Act: -0.0000

Data Index: 785670 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1325493 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6302. Min Act: -0.0000

Data Index: 137683 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.6234. Min Act: -0.0000

Data Index: 267508 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1300817 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.4321. Min Act: -0.0000

Data Index: 708114 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1298786 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.5466. Min Act: -0.0000

Data Index: 55930 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.4056. Min Act: -0.0000

Data Index: 568529 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.4059. Min Act: -0.0000

Data Index: 490287 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.4758. Min Act: -0.0000

Data Index: 549976 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.7059. Min Range: -1.7059

Max Act: 1.4064. Min Act: -0.0000

Data Index: 410801 (C4 (Web Text))

Max Activating Token Index: 713