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

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

Neuron 4131 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.5626. Min Act: -0.0001

Data Index: 920120 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.3679. Min Act: -0.0001

Data Index: 533592 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.3857. Min Act: -0.0001

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.2692. Min Act: -0.0001

Data Index: 709051 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1171538 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1453. Min Act: -0.0001

Data Index: 741657 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1751. Min Act: -0.0001

Data Index: 792918 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1039. Min Act: -0.0001

Data Index: 1230271 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1071. Min Act: -0.0001

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0442. Min Act: -0.0001

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0485. Min Act: -0.0001

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9964. Min Act: -0.0001

Data Index: 659199 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1943. Min Act: -0.0001

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0670. Min Act: -0.0001

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9822. Min Act: -0.0001

Data Index: 203291 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0180. Min Act: -0.0001

Data Index: 343675 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0406. Min Act: -0.0001

Data Index: 740312 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9933. Min Act: -0.0001

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0530. Min Act: -0.0001

Data Index: 1335895 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9711. Min Act: -0.0001

Data Index: 120868 (C4 (Web Text))

Max Activating Token Index: 518