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

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

Neuron 1032 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4055. Min Range: -6.4055

Max Act: 6.2475. Min Act: -0.0000

Data Index: 1045410 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 6.4055. Min Range: -6.4055

Max Act: 6.4055. Min Act: -0.0000

Data Index: 1214127 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 6.4055. Min Range: -6.4055

Max Act: 6.1061. Min Act: -0.0000

Data Index: 920479 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 6.4055. Min Range: -6.4055

Max Act: 5.9581. Min Act: -0.0000

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 6.4055. Min Range: -6.4055

Max Act: 5.3097. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 6.4055. Min Range: -6.4055

Max Act: 5.5443. Min Act: -0.0000

Data Index: 1031956 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.8971. Min Act: -0.0000

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.5237. Min Act: -0.0000

Data Index: 1143889 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.8385. Min Act: -0.0000

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.1746. Min Act: -0.0000

Data Index: 183196 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.5708. Min Act: -0.0000

Data Index: 441198 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.6036. Min Act: -0.0000

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.3012. Min Act: -0.0000

Data Index: 1153628 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.5674. Min Act: -0.0000

Data Index: 171812 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.4199. Min Act: -0.0000

Data Index: 124715 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 6.4055. Min Range: -6.4055

Max Act: 4.4248. Min Act: -0.0000

Data Index: 538257 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 6.4055. Min Range: -6.4055

Max Act: 3.8351. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 6.4055. Min Range: -6.4055

Max Act: 3.8990. Min Act: -0.0000

Data Index: 24769 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 6.4055. Min Range: -6.4055

Max Act: 3.1939. Min Act: -0.0000

Data Index: 130587 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 6.4055. Min Range: -6.4055

Max Act: 3.4542. Min Act: -0.0000

Data Index: 478280 (C4 (Web Text))

Max Activating Token Index: 677