Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1858 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0569. Min Act: -0.0001

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0001

Data Index: 407383 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1188130 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0544. Min Act: -0.0001

Data Index: 147844 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1242769 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0559. Min Act: -0.0001

Data Index: 500213 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0504. Min Act: -0.0001

Data Index: 893732 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0530. Min Act: -0.0001

Data Index: 69251 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1299019 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0511. Min Act: -0.0001

Data Index: 234585 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0489. Min Act: -0.0001

Data Index: 51207 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0481. Min Act: -0.0001

Data Index: 773785 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1043697 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0499. Min Act: -0.0001

Data Index: 678997 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0468. Min Act: -0.0001

Data Index: 876731 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0467. Min Act: -0.0001

Data Index: 382811 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0449. Min Act: -0.0001

Data Index: 805688 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0410. Min Act: -0.0001

Data Index: 989345 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0484. Min Act: -0.0001

Data Index: 980200 (C4 (Web Text))

Max Activating Token Index: 8