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

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

Neuron 2309 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: 4.3049. Min Range: -4.3049

Max Act: 4.3049. Min Act: -0.0000

Data Index: 465453 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 4.3049. Min Range: -4.3049

Max Act: 3.6520. Min Act: -0.0000

Data Index: 1292328 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 4.3049. Min Range: -4.3049

Max Act: 3.5727. Min Act: -0.0000

Data Index: 109048 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.9910. Min Act: -0.0000

Data Index: 924014 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.4825. Min Act: -0.0000

Data Index: 46656 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.7756. Min Act: -0.0000

Data Index: 217279 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.4604. Min Act: -0.0000

Data Index: 1339918 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.3124. Min Act: -0.0000

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.0955. Min Act: -0.0000

Data Index: 235202 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.0963. Min Act: -0.0000

Data Index: 141838 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 4.3049. Min Range: -4.3049

Max Act: 2.0568. Min Act: -0.0000

Data Index: 954405 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.9139. Min Act: -0.0000

Data Index: 487807 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.9982. Min Act: -0.0000

Data Index: 1205685 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.9578. Min Act: -0.0000

Data Index: 72883 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.9756. Min Act: -0.0000

Data Index: 814540 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.7441. Min Act: -0.0000

Data Index: 738237 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.8094. Min Act: -0.0000

Data Index: 941365 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.8884. Min Act: -0.0000

Data Index: 211708 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.7813. Min Act: -0.0000

Data Index: 655873 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 4.3049. Min Range: -4.3049

Max Act: 1.7877. Min Act: -0.0000

Data Index: 653381 (C4 (Web Text))

Max Activating Token Index: 917