Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2606 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0647. Min Act: -0.0001

Data Index: 164618 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0675. Min Act: -0.0001

Data Index: 1100648 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9566. Min Act: -0.0001

Data Index: 642629 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9691. Min Act: -0.0001

Data Index: 598093 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9945. Min Act: -0.0001

Data Index: 1098606 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9589. Min Act: -0.0001

Data Index: 392984 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9452. Min Act: -0.0001

Data Index: 163050 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9147. Min Act: -0.0001

Data Index: 465719 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9135. Min Act: -0.0001

Data Index: 11597 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9290. Min Act: -0.0001

Data Index: 1280171 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1219525 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8954. Min Act: -0.0001

Data Index: 785872 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8829. Min Act: -0.0001

Data Index: 216149 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9382. Min Act: -0.0001

Data Index: 1110377 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8593. Min Act: -0.0001

Data Index: 498135 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8791. Min Act: -0.0001

Data Index: 618995 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1061922 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1280229 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8486. Min Act: -0.0001

Data Index: 576038 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8704. Min Act: -0.0001

Data Index: 606027 (C4 (Web Text))

Max Activating Token Index: 849