Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.8192. Min Act: -0.0000

Data Index: 449787 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6415. Min Act: -0.0000

Data Index: 825050 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6647. Min Act: -0.0000

Data Index: 119583 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.7076. Min Act: -0.0000

Data Index: 855678 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6430. Min Act: -0.0000

Data Index: 777238 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6745. Min Act: -0.0000

Data Index: 611910 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6504. Min Act: -0.0000

Data Index: 651650 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1123040 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1161994 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5754. Min Act: -0.0000

Data Index: 557383 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1327696 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5746. Min Act: -0.0000

Data Index: 440237 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5666. Min Act: -0.0000

Data Index: 600652 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5457. Min Act: -0.0000

Data Index: 677471 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1071490 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5468. Min Act: -0.0000

Data Index: 647751 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5662. Min Act: -0.0000

Data Index: 779182 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1051543 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5181. Min Act: -0.0000

Data Index: 379581 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5239. Min Act: -0.0000

Data Index: 862797 (C4 (Web Text))

Max Activating Token Index: 952