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

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

Neuron 4084 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0002

Data Index: 556161 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0644. Min Act: -0.0002

Data Index: 856792 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0557. Min Act: -0.0002

Data Index: 365061 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0500. Min Act: -0.0002

Data Index: 67352 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0458. Min Act: -0.0002

Data Index: 281929 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0499. Min Act: -0.0002

Data Index: 34593 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0452. Min Act: -0.0002

Data Index: 71361 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0477. Min Act: -0.0002

Data Index: 657906 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0536. Min Act: -0.0002

Data Index: 994105 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1205379 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0574. Min Act: -0.0002

Data Index: 421666 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0444. Min Act: -0.0002

Data Index: 778333 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0520. Min Act: -0.0002

Data Index: 529631 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0484. Min Act: -0.0002

Data Index: 173959 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0409. Min Act: -0.0002

Data Index: 3729 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0449. Min Act: -0.0002

Data Index: 427001 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0439. Min Act: -0.0002

Data Index: 458084 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1046499 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0450. Min Act: -0.0002

Data Index: 499688 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1019548 (C4 (Web Text))

Max Activating Token Index: 490