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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2177 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4851. Min Act: -0.0000

Data Index: 263459 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4040. Min Act: -0.0000

Data Index: 829865 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3841. Min Act: -0.0000

Data Index: 977891 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3551. Min Act: -0.0000

Data Index: 972930 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1058458 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1343796 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1106548 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1319579 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3172. Min Act: -0.0000

Data Index: 20414 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3314. Min Act: -0.0000

Data Index: 358039 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1324943 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3454. Min Act: -0.0000

Data Index: 586762 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3222. Min Act: -0.0000

Data Index: 195787 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3197. Min Act: 0.0001

Data Index: 966434 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3179. Min Act: 0.0001

Data Index: 1044036 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3266. Min Act: 0.0000

Data Index: 101150 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3169. Min Act: -0.0000

Data Index: 840258 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3149. Min Act: -0.0000

Data Index: 24535 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3012. Min Act: -0.0000

Data Index: 256494 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1146670 (C4 (Web Text))

Max Activating Token Index: 462