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

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

Neuron 1603 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0712. Min Act: -0.0002

Data Index: 596533 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0697. Min Act: -0.0002

Data Index: 491068 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0651. Min Act: -0.0002

Data Index: 170228 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1345233 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0650. Min Act: -0.0002

Data Index: 385651 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0646. Min Act: -0.0002

Data Index: 180494 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0634. Min Act: -0.0002

Data Index: 221380 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0589. Min Act: -0.0003

Data Index: 77090 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0576. Min Act: -0.0002

Data Index: 299010 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0569. Min Act: -0.0002

Data Index: 802897 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0565. Min Act: -0.0001

Data Index: 224972 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1063869 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1309237 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0543. Min Act: -0.0002

Data Index: 555377 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0548. Min Act: -0.0002

Data Index: 811453 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1125354 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0541. Min Act: -0.0002

Data Index: 836390 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0530. Min Act: -0.0002

Data Index: 569973 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0528. Min Act: -0.0002

Data Index: 608723 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0525. Min Act: -0.0002

Data Index: 161140 (C4 (Web Text))

Max Activating Token Index: 12