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

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

Neuron 290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.1589. Min Act: -0.0001

Data Index: 483973 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.1058. Min Act: -0.0001

Data Index: 1578961 (Python Code)

Max Activating Token Index: 790

Text #2

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9841. Min Act: -0.0001

Data Index: 12264 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.0265. Min Act: -0.0001

Data Index: 832653 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9568. Min Act: -0.0001

Data Index: 93619 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9572. Min Act: -0.0001

Data Index: 1124933 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8488. Min Act: -0.0001

Data Index: 384349 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9250. Min Act: -0.0001

Data Index: 372729 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9199. Min Act: -0.0001

Data Index: 522929 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9433. Min Act: -0.0001

Data Index: 1402708 (Python Code)

Max Activating Token Index: 127

Text #10

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9414. Min Act: -0.0001

Data Index: 721684 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9674. Min Act: -0.0001

Data Index: 416663 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9660. Min Act: -0.0001

Data Index: 235378 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9602. Min Act: -0.0001

Data Index: 43921 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8977. Min Act: -0.0001

Data Index: 784767 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9314. Min Act: -0.0001

Data Index: 461872 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8870. Min Act: -0.0001

Data Index: 25727 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1231758 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8473. Min Act: -0.0001

Data Index: 412434 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9024. Min Act: -0.0001

Data Index: 494568 (C4 (Web Text))

Max Activating Token Index: 669