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

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

Neuron 642 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: 0.4827. Min Range: -0.4827

Max Act: 0.4827. Min Act: -0.0000

Data Index: 26063 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4805. Min Act: -0.0000

Data Index: 551801 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4288. Min Act: -0.0000

Data Index: 468121 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4111. Min Act: -0.0000

Data Index: 593452 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3779. Min Act: -0.0000

Data Index: 96706 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3911. Min Act: -0.0000

Data Index: 22447 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3750. Min Act: -0.0000

Data Index: 452305 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1158245 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3606. Min Act: -0.0000

Data Index: 686198 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3366. Min Act: -0.0000

Data Index: 489348 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1219341 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3338. Min Act: -0.0000

Data Index: 355091 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3567. Min Act: -0.0000

Data Index: 12521 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3412. Min Act: -0.0000

Data Index: 687086 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3580. Min Act: -0.0000

Data Index: 12017 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3402. Min Act: -0.0000

Data Index: 492683 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3371. Min Act: -0.0000

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3143. Min Act: -0.0000

Data Index: 8486 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3130. Min Act: -0.0000

Data Index: 615288 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3235. Min Act: -0.0000

Data Index: 889642 (C4 (Web Text))

Max Activating Token Index: 459