Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1509 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1357598 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0002

Data Index: 967594 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0524. Min Act: -0.0002

Data Index: 11545 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0497. Min Act: -0.0002

Data Index: 276804 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0476. Min Act: -0.0002

Data Index: 32105 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0493. Min Act: -0.0002

Data Index: 254357 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0488. Min Act: -0.0002

Data Index: 666788 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0465. Min Act: -0.0002

Data Index: 43944 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1274113 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0455. Min Act: -0.0002

Data Index: 29745 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1355956 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0458. Min Act: -0.0002

Data Index: 319898 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0459. Min Act: -0.0002

Data Index: 629612 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0452. Min Act: -0.0002

Data Index: 9525 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1305077 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0463. Min Act: -0.0002

Data Index: 558855 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1290562 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0466. Min Act: -0.0002

Data Index: 72220 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0463. Min Act: -0.0002

Data Index: 746340 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1123979 (C4 (Web Text))

Max Activating Token Index: 536