Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 30 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 910617 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1273651 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0541. Min Act: -0.0002

Data Index: 527553 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1599066 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1501106 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0526. Min Act: -0.0002

Data Index: 131760 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1596070 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0518. Min Act: -0.0002

Data Index: 878318 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1404914 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1645141 (Python Code)

Max Activating Token Index: 234

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0494. Min Act: -0.0002

Data Index: 848241 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0508. Min Act: -0.0002

Data Index: 538497 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1544767 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1537189 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1302621 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1614844 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1071927 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1345876 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1636402 (Python Code)

Max Activating Token Index: 497

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0482. Min Act: -0.0002

Data Index: 137722 (C4 (Web Text))

Max Activating Token Index: 728