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

Dataset: The Pile

Neuron 3391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5026. Min Act: -0.0000

Data Index: 980521 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1047901 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4667. Min Act: -0.0000

Data Index: 390253 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4763. Min Act: -0.0000

Data Index: 502216 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4801. Min Act: -0.0000

Data Index: 162590 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4452. Min Act: -0.0000

Data Index: 734691 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4373. Min Act: -0.0000

Data Index: 765511 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4322. Min Act: -0.0000

Data Index: 817202 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4305. Min Act: -0.0000

Data Index: 845180 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4403. Min Act: -0.0000

Data Index: 19454 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1959990 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4476. Min Act: -0.0000

Data Index: 796121 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1045394 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1910619 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1831642 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1552797 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4323. Min Act: -0.0000

Data Index: 206834 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1391894 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4149. Min Act: -0.0000

Data Index: 513798 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1473663 (The Pile)

Max Activating Token Index: 256