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

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

Neuron 2021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3883. Min Act: -0.0001

Data Index: 535044 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3610. Min Act: -0.0002

Data Index: 1337060 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1233888 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3712. Min Act: -0.0001

Data Index: 290685 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3534. Min Act: -0.0002

Data Index: 1215034 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3220. Min Act: -0.0001

Data Index: 685066 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3621. Min Act: -0.0001

Data Index: 268018 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3468. Min Act: -0.0001

Data Index: 994850 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3668. Min Act: -0.0002

Data Index: 792629 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3426. Min Act: -0.0002

Data Index: 699662 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3224. Min Act: -0.0002

Data Index: 477203 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3499. Min Act: -0.0002

Data Index: 595755 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3476. Min Act: -0.0002

Data Index: 575538 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3705. Min Act: -0.0002

Data Index: 1339682 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1045318 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3195. Min Act: -0.0002

Data Index: 725517 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3315. Min Act: -0.0001

Data Index: 203482 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3004. Min Act: -0.0001

Data Index: 16302 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3082. Min Act: -0.0002

Data Index: 744513 (C4 (Web Text))

Max Activating Token Index: 863