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

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

Neuron 2469 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: 2.2881. Min Range: -2.2881

Max Act: 2.1522. Min Act: -0.0000

Data Index: 923423 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.2881. Min Act: -0.0000

Data Index: 99409 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.2424. Min Act: -0.0000

Data Index: 1147244 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1138875 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.1296. Min Act: -0.0000

Data Index: 487058 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.1490. Min Act: -0.0000

Data Index: 1205467 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 2.2881. Min Range: -2.2881

Max Act: 2.0370. Min Act: -0.0000

Data Index: 374804 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.8868. Min Act: -0.0000

Data Index: 1169961 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.8145. Min Act: -0.0000

Data Index: 1302625 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.8834. Min Act: -0.0000

Data Index: 397424 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7365. Min Act: -0.0000

Data Index: 344570 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7040. Min Act: -0.0000

Data Index: 925959 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.8055. Min Act: -0.0000

Data Index: 377514 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7616. Min Act: -0.0000

Data Index: 187203 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.8691. Min Act: -0.0000

Data Index: 1035240 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7526. Min Act: -0.0000

Data Index: 671229 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7346. Min Act: -0.0000

Data Index: 156948 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7375. Min Act: -0.0000

Data Index: 1212314 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.6384. Min Act: -0.0000

Data Index: 218287 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 2.2881. Min Range: -2.2881

Max Act: 1.7302. Min Act: -0.0000

Data Index: 559306 (C4 (Web Text))

Max Activating Token Index: 809