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

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

Neuron 3860 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: 0.0603. Min Range: -0.0603

Max Act: 0.0569. Min Act: -0.0002

Data Index: 491161 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1292145 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0574. Min Act: -0.0002

Data Index: 678175 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1287798 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0567. Min Act: -0.0002

Data Index: 180718 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0002

Data Index: 143239 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0543. Min Act: -0.0002

Data Index: 414958 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0513. Min Act: -0.0002

Data Index: 858819 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0538. Min Act: -0.0002

Data Index: 61664 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0483. Min Act: -0.0002

Data Index: 615652 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0552. Min Act: -0.0001

Data Index: 706567 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0511. Min Act: -0.0002

Data Index: 252844 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1249675 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0530. Min Act: -0.0002

Data Index: 20882 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0516. Min Act: -0.0001

Data Index: 77145 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0525. Min Act: -0.0001

Data Index: 639338 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0509. Min Act: -0.0002

Data Index: 713994 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0491. Min Act: -0.0002

Data Index: 112751 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0502. Min Act: -0.0001

Data Index: 955692 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1025396 (C4 (Web Text))

Max Activating Token Index: 778