Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1298 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.3575. Min Act: -0.0001

Data Index: 362771 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.3863. Min Act: -0.0001

Data Index: 458309 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.3254. Min Act: -0.0001

Data Index: 20023 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2910. Min Act: -0.0001

Data Index: 203871 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2661. Min Act: -0.0001

Data Index: 593003 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2851. Min Act: -0.0001

Data Index: 970191 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2897. Min Act: -0.0001

Data Index: 250900 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2491. Min Act: -0.0001

Data Index: 444392 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2663. Min Act: -0.0001

Data Index: 672772 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1234831 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2627. Min Act: -0.0001

Data Index: 1308747 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2412. Min Act: -0.0001

Data Index: 475384 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2568. Min Act: -0.0001

Data Index: 565202 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2399. Min Act: -0.0001

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2416. Min Act: -0.0001

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2439. Min Act: -0.0001

Data Index: 439193 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2453. Min Act: -0.0001

Data Index: 1085704 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2674. Min Act: -0.0001

Data Index: 183045 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.3863. Min Range: -0.3863

Max Act: 0.2401. Min Act: -0.0001

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 845