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

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

Neuron 990 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4793. Min Act: -0.0001

Data Index: 749824 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4649. Min Act: -0.0002

Data Index: 811913 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4572. Min Act: -0.0002

Data Index: 389923 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4559. Min Act: -0.0002

Data Index: 1096148 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4623. Min Act: -0.0002

Data Index: 463509 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4519. Min Act: -0.0002

Data Index: 494852 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4572. Min Act: -0.0002

Data Index: 585663 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4381. Min Act: -0.0002

Data Index: 356653 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4386. Min Act: -0.0002

Data Index: 43343 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4332. Min Act: -0.0002

Data Index: 867640 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4228. Min Act: -0.0002

Data Index: 1105897 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4235. Min Act: -0.0002

Data Index: 8598 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4339. Min Act: -0.0002

Data Index: 819079 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4253. Min Act: -0.0002

Data Index: 511516 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4223. Min Act: -0.0002

Data Index: 355381 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4258. Min Act: -0.0002

Data Index: 1252792 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4185. Min Act: -0.0002

Data Index: 458132 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4261. Min Act: -0.0002

Data Index: 426689 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4164. Min Act: -0.0002

Data Index: 828970 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4137. Min Act: -0.0002

Data Index: 676614 (C4 (Web Text))

Max Activating Token Index: 533