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

Dataset: The Pile

Neuron 4850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1512005 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1333788 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1226166 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1324852 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9764. Min Act: 0.0000

Data Index: 198123 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1339724 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0682. Min Act: -0.0000

Data Index: 250625 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1431868 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1421660 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1818637 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8186. Min Act: 0.0001

Data Index: 1154982 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1698310 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.7312. Min Act: -0.0000

Data Index: 676326 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8409. Min Act: -0.0000

Data Index: 730284 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8010. Min Act: -0.0000

Data Index: 167263 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8327. Min Act: -0.0000

Data Index: 674189 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1126989 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.7796. Min Act: -0.0000

Data Index: 175237 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1142007 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1021580 (The Pile)

Max Activating Token Index: 523