Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.5700. Min Act: -0.0000

Data Index: 1066640 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.3408. Min Act: -0.0000

Data Index: 735812 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.4616. Min Act: -0.0000

Data Index: 513326 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.3108. Min Act: -0.0000

Data Index: 680124 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.2339. Min Act: -0.0000

Data Index: 199269 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1862. Min Act: -0.0000

Data Index: 918704 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1202. Min Act: -0.0000

Data Index: 796257 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.2313. Min Act: -0.0000

Data Index: 1113640 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1013. Min Act: -0.0000

Data Index: 915987 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1328380 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8678. Min Act: -0.0000

Data Index: 1214325 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9144. Min Act: -0.0000

Data Index: 866412 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9289. Min Act: -0.0000

Data Index: 351074 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0108. Min Act: -0.0000

Data Index: 1645487 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8759. Min Act: -0.0000

Data Index: 1349584 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1018155 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8495. Min Act: -0.0000

Data Index: 414418 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1224362 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8209. Min Act: -0.0000

Data Index: 109515 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1177861 (C4 (Web Text))

Max Activating Token Index: 124