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

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

Neuron 4853 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.4065. Min Act: -0.0000

Data Index: 325609 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.5441. Min Act: -0.0000

Data Index: 463383 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.3556. Min Act: -0.0000

Data Index: 996383 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.2705. Min Act: -0.0000

Data Index: 858507 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.2640. Min Act: -0.0000

Data Index: 402775 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1068199 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.2551. Min Act: -0.0000

Data Index: 319697 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.2526. Min Act: -0.0000

Data Index: 616175 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1388. Min Act: -0.0000

Data Index: 954935 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1758. Min Act: -0.0000

Data Index: 152113 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0887. Min Act: -0.0000

Data Index: 9700 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1440. Min Act: -0.0000

Data Index: 829491 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1458. Min Act: -0.0000

Data Index: 638757 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1478. Min Act: -0.0000

Data Index: 101086 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1275. Min Act: -0.0000

Data Index: 182205 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1215. Min Act: -0.0000

Data Index: 223024 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0505. Min Act: -0.0000

Data Index: 150390 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0493. Min Act: -0.0000

Data Index: 301640 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1116. Min Act: -0.0000

Data Index: 305640 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1183497 (C4 (Web Text))

Max Activating Token Index: 21