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

Dataset: The Pile

Neuron 2303 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: 0.5740. Min Range: -0.5740

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1241309 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1092891 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1241681 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1443612 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5330. Min Act: -0.0000

Data Index: 483548 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5101. Min Act: -0.0000

Data Index: 840641 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1149875 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4753. Min Act: -0.0000

Data Index: 299011 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1872106 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5030. Min Act: -0.0000

Data Index: 266120 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4881. Min Act: -0.0000

Data Index: 683628 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1970844 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1751693 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1858592 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4831. Min Act: -0.0000

Data Index: 378660 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1612048 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4304. Min Act: -0.0000

Data Index: 118728 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4500. Min Act: -0.0000

Data Index: 669070 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4556. Min Act: 0.0000

Data Index: 1765087 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4307. Min Act: -0.0000

Data Index: 652038 (The Pile)

Max Activating Token Index: 632