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

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

Neuron 5587 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: 5.5454. Min Range: -5.5454

Max Act: 5.4512. Min Act: -0.0000

Data Index: 958553 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 5.5454. Min Range: -5.5454

Max Act: 5.5454. Min Act: -0.0000

Data Index: 112177 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 5.5454. Min Range: -5.5454

Max Act: 5.2373. Min Act: -0.0000

Data Index: 522090 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.6145. Min Act: -0.0000

Data Index: 953269 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.9108. Min Act: -0.0000

Data Index: 875773 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 5.5454. Min Range: -5.5454

Max Act: 5.0959. Min Act: -0.0000

Data Index: 667192 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.7007. Min Act: -0.0000

Data Index: 559586 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.8340. Min Act: -0.0000

Data Index: 125679 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.4214. Min Act: -0.0000

Data Index: 1294510 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.4231. Min Act: -0.0000

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 5.5454. Min Range: -5.5454

Max Act: 5.0020. Min Act: -0.0000

Data Index: 789597 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.3031. Min Act: -0.0000

Data Index: 145853 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.2597. Min Act: -0.0000

Data Index: 1272240 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.4178. Min Act: -0.0000

Data Index: 1350813 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.5756. Min Act: -0.0000

Data Index: 1287974 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.3612. Min Act: -0.0000

Data Index: 1154078 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.3543. Min Act: -0.0000

Data Index: 506109 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.3162. Min Act: -0.0000

Data Index: 582656 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.4890. Min Act: -0.0000

Data Index: 1322530 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 5.5454. Min Range: -5.5454

Max Act: 4.3236. Min Act: -0.0000

Data Index: 160702 (C4 (Web Text))

Max Activating Token Index: 781