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

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

Neuron 2730 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9886. Min Act: -0.0001

Data Index: 1093790 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7653. Min Act: -0.0001

Data Index: 839805 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7269. Min Act: -0.0001

Data Index: 766354 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1238452 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8305. Min Act: -0.0001

Data Index: 993183 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7619. Min Act: -0.0001

Data Index: 541841 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6468. Min Act: -0.0001

Data Index: 352368 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7210. Min Act: -0.0001

Data Index: 1222021 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6987. Min Act: -0.0001

Data Index: 496049 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6930. Min Act: -0.0001

Data Index: 1205572 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1001068 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6690. Min Act: -0.0001

Data Index: 751269 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7126. Min Act: -0.0001

Data Index: 432310 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6809. Min Act: -0.0001

Data Index: 375123 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6626. Min Act: -0.0001

Data Index: 900458 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6550. Min Act: -0.0001

Data Index: 213451 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1330395 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6681. Min Act: -0.0001

Data Index: 742610 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6645. Min Act: -0.0001

Data Index: 678141 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6562. Min Act: -0.0001

Data Index: 241111 (C4 (Web Text))

Max Activating Token Index: 201