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

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

Neuron 4938 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: 4.8577. Min Range: -4.8577

Max Act: 4.8577. Min Act: -0.0000

Data Index: 402099 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 4.8577. Min Range: -4.8577

Max Act: 4.3200. Min Act: -0.0000

Data Index: 514103 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.9267. Min Act: -0.0000

Data Index: 448883 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 4.8577. Min Range: -4.8577

Max Act: 4.0709. Min Act: -0.0000

Data Index: 960528 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.7282. Min Act: -0.0000

Data Index: 589479 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.7251. Min Act: -0.0000

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.7639. Min Act: -0.0000

Data Index: 703651 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.8586. Min Act: -0.0000

Data Index: 830439 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.3205. Min Act: -0.0000

Data Index: 202483 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.3848. Min Act: -0.0000

Data Index: 235558 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 4.8577. Min Range: -4.8577

Max Act: 3.0448. Min Act: -0.0000

Data Index: 430984 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.8943. Min Act: -0.0000

Data Index: 818527 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.9802. Min Act: -0.0000

Data Index: 518668 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.9707. Min Act: -0.0000

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.9225. Min Act: -0.0000

Data Index: 920120 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.9086. Min Act: -0.0000

Data Index: 750693 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.9557. Min Act: -0.0000

Data Index: 1254387 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.7833. Min Act: -0.0000

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.6801. Min Act: -0.0000

Data Index: 1332175 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 4.8577. Min Range: -4.8577

Max Act: 2.6472. Min Act: -0.0000

Data Index: 127624 (C4 (Web Text))

Max Activating Token Index: 175