Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4791 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1290858 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1677. Min Act: -0.0000

Data Index: 736253 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1164925 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1030950 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1105. Min Act: -0.0000

Data Index: 172934 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1309587 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1177. Min Act: -0.0000

Data Index: 359885 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0937. Min Act: -0.0000

Data Index: 87496 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0958. Min Act: -0.0000

Data Index: 245385 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1189. Min Act: -0.0000

Data Index: 426873 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0850. Min Act: -0.0000

Data Index: 483346 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0813. Min Act: -0.0000

Data Index: 267485 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1254414 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0729. Min Act: -0.0000

Data Index: 995178 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1254125 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1071110 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0549. Min Act: -0.0000

Data Index: 269440 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0680. Min Act: -0.0000

Data Index: 295834 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0566. Min Act: -0.0000

Data Index: 165548 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.0623. Min Act: -0.0000

Data Index: 171446 (C4 (Web Text))

Max Activating Token Index: 945