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

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

Neuron 5107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.4124. Min Act: -0.0000

Data Index: 482234 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.3370. Min Act: -0.0000

Data Index: 168672 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.2573. Min Act: -0.0000

Data Index: 448447 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.1772. Min Act: -0.0000

Data Index: 891551 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.1470. Min Act: -0.0000

Data Index: 891091 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.1120. Min Act: -0.0000

Data Index: 480511 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0549. Min Act: -0.0000

Data Index: 31 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.1023. Min Act: -0.0000

Data Index: 396710 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1033799 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0245. Min Act: -0.0000

Data Index: 745084 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0883. Min Act: -0.0000

Data Index: 342067 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.4124. Min Range: -1.4124

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1033744 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0372. Min Act: -0.0000

Data Index: 849369 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.4124. Min Range: -1.4124

Max Act: 0.9735. Min Act: -0.0000

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.4124. Min Range: -1.4124

Max Act: 0.9975. Min Act: -0.0000

Data Index: 308542 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1044204 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0251. Min Act: -0.0000

Data Index: 311523 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0107. Min Act: -0.0000

Data Index: 356241 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1077332 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.4124. Min Range: -1.4124

Max Act: 1.0551. Min Act: -0.0000

Data Index: 520655 (C4 (Web Text))

Max Activating Token Index: 579