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

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

Neuron 3858 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4544. Min Act: -0.0000

Data Index: 81990 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1056675 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4665. Min Act: -0.0000

Data Index: 588862 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1078476 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4465. Min Act: -0.0000

Data Index: 192588 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4478. Min Act: -0.0000

Data Index: 933160 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1308428 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4153. Min Act: -0.0000

Data Index: 542604 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3970. Min Act: -0.0000

Data Index: 656245 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1319546 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3903. Min Act: -0.0000

Data Index: 585315 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4149. Min Act: -0.0001

Data Index: 320976 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1014855 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3695. Min Act: -0.0000

Data Index: 782793 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1125148 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3288. Min Act: -0.0000

Data Index: 954810 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3574. Min Act: -0.0000

Data Index: 398570 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1334648 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1187819 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3654. Min Act: -0.0000

Data Index: 814960 (C4 (Web Text))

Max Activating Token Index: 763