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

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

Neuron 684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0548. Min Act: -0.0001

Data Index: 236077 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0367. Min Act: -0.0001

Data Index: 754976 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0553. Min Act: -0.0001

Data Index: 593500 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0170. Min Act: -0.0001

Data Index: 9757 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0021. Min Act: -0.0001

Data Index: 1353367 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1141229 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9085. Min Act: -0.0001

Data Index: 1016449 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9856. Min Act: -0.0001

Data Index: 81051 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0399. Min Act: -0.0001

Data Index: 635754 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0314. Min Act: -0.0001

Data Index: 1292662 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9742. Min Act: -0.0001

Data Index: 1275800 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9941. Min Act: -0.0001

Data Index: 269108 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9904. Min Act: -0.0001

Data Index: 779059 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0507. Min Act: -0.0001

Data Index: 702582 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.0553. Min Range: -1.0553

Max Act: 1.0022. Min Act: -0.0001

Data Index: 384197 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9430. Min Act: -0.0001

Data Index: 595430 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9726. Min Act: -0.0001

Data Index: 743950 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9976. Min Act: -0.0001

Data Index: 1027619 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9373. Min Act: -0.0001

Data Index: 861583 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.0553. Min Range: -1.0553

Max Act: 0.9302. Min Act: -0.0001

Data Index: 797601 (C4 (Web Text))

Max Activating Token Index: 432