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

Dataset: The Pile

Neuron 1730 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1334450 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1631784 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1081132 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1018548 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1061650 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1301099 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0790. Min Act: -0.0000

Data Index: 306984 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1326223 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1434691 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1182198 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1298. Min Act: -0.0000

Data Index: 963517 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1610. Min Act: -0.0000

Data Index: 116642 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0917. Min Act: -0.0000

Data Index: 839140 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1068. Min Act: -0.0000

Data Index: 407370 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1746082 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1897878 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1782163 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1682628 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0645. Min Act: -0.0000

Data Index: 350138 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1330173 (The Pile)

Max Activating Token Index: 756