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

Dataset: The Pile

Neuron 2438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.8530. Min Act: -0.0000

Data Index: 1602968 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.4248. Min Act: -0.0000

Data Index: 562664 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.1599. Min Act: -0.0000

Data Index: 1052155 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.5218. Min Act: -0.0000

Data Index: 1350116 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.4836. Min Act: -0.0000

Data Index: 660260 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.5159. Min Act: -0.0000

Data Index: 1032628 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.4983. Min Act: -0.0000

Data Index: 651983 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.1229. Min Act: -0.0000

Data Index: 1497204 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.9630. Min Act: -0.0000

Data Index: 578193 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.4474. Min Act: -0.0000

Data Index: 262894 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.8506. Min Act: -0.0000

Data Index: 366720 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.8548. Min Act: -0.0000

Data Index: 1550401 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.3345. Min Act: -0.0000

Data Index: 1761929 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.1291. Min Act: -0.0000

Data Index: 1266751 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.7755. Min Act: -0.0000

Data Index: 276483 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.7575. Min Act: -0.0000

Data Index: 1372548 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.8544. Min Act: -0.0000

Data Index: 239095 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.6073. Min Act: -0.0000

Data Index: 470472 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.9495. Min Act: -0.0000

Data Index: 1628045 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.7600. Min Act: -0.0000

Data Index: 1210436 (The Pile)

Max Activating Token Index: 135