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

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

Neuron 1549 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1021612 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1614117 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0676. Min Act: -0.0003

Data Index: 543670 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1369806 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0638. Min Act: -0.0003

Data Index: 206928 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1225007 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0579. Min Act: -0.0003

Data Index: 861269 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0568. Min Act: -0.0003

Data Index: 67265 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1053199 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0568. Min Act: -0.0003

Data Index: 773782 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0545. Min Act: -0.0003

Data Index: 141101 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0565. Min Act: -0.0003

Data Index: 694442 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0569. Min Act: -0.0003

Data Index: 251040 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0547. Min Act: -0.0003

Data Index: 484089 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0522. Min Act: -0.0003

Data Index: 910376 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1195448 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1396262 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0555. Min Act: -0.0003

Data Index: 318009 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1090728 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0552. Min Act: -0.0003

Data Index: 563150 (C4 (Web Text))

Max Activating Token Index: 665