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

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

Neuron 3137 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.9167. Min Act: -0.0000

Data Index: 736131 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.5232. Min Act: -0.0000

Data Index: 1333197 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3194. Min Act: -0.0000

Data Index: 980424 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.9032. Min Act: -0.0000

Data Index: 349995 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7990. Min Act: -0.0000

Data Index: 536235 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7421. Min Act: -0.0000

Data Index: 1290469 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.8344. Min Act: -0.0000

Data Index: 198866 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7710. Min Act: -0.0000

Data Index: 537166 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7330. Min Act: -0.0000

Data Index: 221080 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7352. Min Act: -0.0000

Data Index: 259220 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.7075. Min Act: -0.0000

Data Index: 882485 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.6532. Min Act: -0.0000

Data Index: 267287 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.6260. Min Act: -0.0000

Data Index: 840467 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.6821. Min Act: -0.0000

Data Index: 337996 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.5184. Min Act: -0.0000

Data Index: 920569 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.4771. Min Act: -0.0000

Data Index: 678445 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.5460. Min Act: -0.0000

Data Index: 714250 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.5385. Min Act: -0.0000

Data Index: 112577 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.5953. Min Act: -0.0000

Data Index: 17154 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.4572. Min Act: -0.0000

Data Index: 732326 (C4 (Web Text))

Max Activating Token Index: 147