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

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

Neuron 1863 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: 0.4635. Min Range: -0.4635

Max Act: 0.4635. Min Act: -0.0000

Data Index: 156615 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4345. Min Act: -0.0000

Data Index: 528096 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4102. Min Act: -0.0000

Data Index: 814075 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4132. Min Act: -0.0000

Data Index: 466952 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3845. Min Act: -0.0000

Data Index: 989457 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3796. Min Act: -0.0000

Data Index: 728162 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3869. Min Act: -0.0000

Data Index: 67465 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3701. Min Act: -0.0000

Data Index: 229240 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3864. Min Act: -0.0000

Data Index: 164359 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3928. Min Act: -0.0000

Data Index: 304238 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1101107 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3610. Min Act: -0.0001

Data Index: 191022 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3890. Min Act: -0.0000

Data Index: 188301 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3450. Min Act: -0.0000

Data Index: 511827 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1309965 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3896. Min Act: -0.0000

Data Index: 406774 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3620. Min Act: -0.0001

Data Index: 364131 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1190647 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1058543 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3124. Min Act: -0.0000

Data Index: 307126 (C4 (Web Text))

Max Activating Token Index: 596