Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2901 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1010328 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1003654 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5326. Min Act: -0.0000

Data Index: 968259 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1181988 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1281786 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4777. Min Act: -0.0000

Data Index: 289412 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5100. Min Act: -0.0000

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4913. Min Act: -0.0000

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1126771 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4894. Min Act: -0.0000

Data Index: 680143 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4650. Min Act: -0.0000

Data Index: 927040 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4729. Min Act: -0.0000

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4642. Min Act: -0.0000

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4511. Min Act: -0.0000

Data Index: 885560 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4817. Min Act: -0.0000

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1549636 (Python Code)

Max Activating Token Index: 110

Text #16

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1270631 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1486726 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4648. Min Act: -0.0000

Data Index: 473473 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4597. Min Act: -0.0000

Data Index: 265496 (C4 (Web Text))

Max Activating Token Index: 108