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

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

Neuron 183 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.6618. Min Act: -0.0001

Data Index: 172524 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1200173 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4946. Min Act: -0.0001

Data Index: 1037982 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4695. Min Act: -0.0001

Data Index: 973490 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4998. Min Act: -0.0001

Data Index: 530911 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4325. Min Act: -0.0001

Data Index: 1015499 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4635. Min Act: -0.0001

Data Index: 1034679 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4362. Min Act: -0.0001

Data Index: 154933 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4319. Min Act: -0.0001

Data Index: 428835 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4056. Min Act: -0.0001

Data Index: 700541 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.4002. Min Act: -0.0001

Data Index: 888777 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3732. Min Act: -0.0001

Data Index: 564945 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3813. Min Act: -0.0001

Data Index: 1305227 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3837. Min Act: -0.0001

Data Index: 733896 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1310681 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1179128 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1213410 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3484. Min Act: -0.0001

Data Index: 1080758 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3603. Min Act: -0.0001

Data Index: 111046 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.6618. Min Range: -0.6618

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1346038 (C4 (Web Text))

Max Activating Token Index: 992