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

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

Neuron 4436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.5564. Min Act: -0.0000

Data Index: 729764 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.5426. Min Act: -0.0000

Data Index: 719698 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4324. Min Act: -0.0000

Data Index: 843398 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4263. Min Act: -0.0000

Data Index: 73973 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4022. Min Act: -0.0000

Data Index: 668718 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3999. Min Act: -0.0001

Data Index: 942425 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3926. Min Act: -0.0000

Data Index: 814098 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1227865 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3700. Min Act: -0.0000

Data Index: 849607 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3640. Min Act: -0.0000

Data Index: 153664 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3668. Min Act: -0.0000

Data Index: 326430 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3654. Min Act: -0.0000

Data Index: 463609 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3411. Min Act: -0.0000

Data Index: 272775 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3533. Min Act: -0.0000

Data Index: 543059 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3314. Min Act: -0.0001

Data Index: 778551 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3644. Min Act: -0.0000

Data Index: 416337 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3408. Min Act: -0.0000

Data Index: 4949 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3038. Min Act: -0.0000

Data Index: 83464 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1160250 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1311980 (C4 (Web Text))

Max Activating Token Index: 879