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

Dataset: The Pile

Neuron 318 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.7539. Min Act: -0.0000

Data Index: 1172083 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5142. Min Act: -0.0000

Data Index: 1475102 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.6057. Min Act: -0.0000

Data Index: 424785 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4905. Min Act: -0.0000

Data Index: 1294249 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.6254. Min Act: -0.0000

Data Index: 737505 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5063. Min Act: -0.0000

Data Index: 43650 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.2996. Min Act: -0.0000

Data Index: 1405721 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.2892. Min Act: -0.0000

Data Index: 1767694 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.2605. Min Act: -0.0000

Data Index: 454590 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1665976 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.2356. Min Act: -0.0000

Data Index: 620809 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3779. Min Act: -0.0000

Data Index: 712631 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5245. Min Act: -0.0000

Data Index: 45584 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3681. Min Act: -0.0000

Data Index: 598793 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3598. Min Act: -0.0000

Data Index: 81681 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3366. Min Act: -0.0000

Data Index: 1902050 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3577. Min Act: -0.0000

Data Index: 1564880 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3652. Min Act: -0.0000

Data Index: 1807367 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4921. Min Act: -0.0000

Data Index: 934343 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.2133. Min Act: -0.0000

Data Index: 1525140 (The Pile)

Max Activating Token Index: 344