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

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

Neuron 822 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.6432. Min Act: -0.0001

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 4.0447. Min Range: -4.0447

Max Act: 4.0447. Min Act: -0.0001

Data Index: 725599 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.5413. Min Act: -0.0000

Data Index: 884809 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.4864. Min Act: -0.0000

Data Index: 1285639 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.1631. Min Act: -0.0001

Data Index: 6323 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3126. Min Act: -0.0000

Data Index: 626821 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.1449. Min Act: -0.0001

Data Index: 1042649 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.1669. Min Act: -0.0000

Data Index: 1351274 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.0162. Min Act: -0.0000

Data Index: 268833 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.1455. Min Act: -0.0000

Data Index: 462878 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.0899. Min Act: -0.0000

Data Index: 567511 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.9992. Min Act: -0.0000

Data Index: 816342 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.2773. Min Act: -0.0000

Data Index: 428662 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.0648. Min Act: -0.0001

Data Index: 928200 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.8430. Min Act: -0.0001

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.7931. Min Act: -0.0001

Data Index: 1089943 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.2960. Min Act: -0.0000

Data Index: 517921 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.8464. Min Act: -0.0000

Data Index: 515653 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.6122. Min Act: -0.0000

Data Index: 943966 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 4.0447. Min Range: -4.0447

Max Act: 2.7115. Min Act: -0.0000

Data Index: 490683 (C4 (Web Text))

Max Activating Token Index: 133