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

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

Neuron 3344 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: 1.2659. Min Range: -1.2659

Max Act: 1.2659. Min Act: -0.0000

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.0938. Min Act: -0.0001

Data Index: 391065 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1142619 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.9251. Min Act: -0.0000

Data Index: 892962 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1042190 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1020145 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8781. Min Act: -0.0001

Data Index: 330198 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1147700 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8405. Min Act: -0.0000

Data Index: 88763 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8912. Min Act: -0.0000

Data Index: 149608 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1343991 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8366. Min Act: -0.0000

Data Index: 501037 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7882. Min Act: -0.0000

Data Index: 631483 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8887. Min Act: -0.0000

Data Index: 87685 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7721. Min Act: -0.0000

Data Index: 920685 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8203. Min Act: -0.0000

Data Index: 386532 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7873. Min Act: -0.0000

Data Index: 14800 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7764. Min Act: -0.0000

Data Index: 111925 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1196827 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7868. Min Act: -0.0000

Data Index: 760619 (C4 (Web Text))

Max Activating Token Index: 182