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

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

Neuron 4015 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: 2.0637. Min Range: -2.0637

Max Act: 2.0637. Min Act: -0.0000

Data Index: 1367128 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.9438. Min Act: -0.0000

Data Index: 1393196 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1407413 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7505. Min Act: -0.0000

Data Index: 616083 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1426350 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1052406 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7900. Min Act: -0.0000

Data Index: 1472919 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7463. Min Act: -0.0000

Data Index: 793702 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1472986 (Python Code)

Max Activating Token Index: 672

Text #9

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1533269 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1610683 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.7010. Min Act: -0.0000

Data Index: 532709 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.6781. Min Act: -0.0000

Data Index: 501159 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.6339. Min Act: -0.0000

Data Index: 105884 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.5200. Min Act: -0.0000

Data Index: 311258 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.6226. Min Act: -0.0000

Data Index: 397976 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1484737 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.5471. Min Act: -0.0000

Data Index: 313131 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1400008 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 2.0637. Min Range: -2.0637

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1210513 (C4 (Web Text))

Max Activating Token Index: 907