Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0000

Data Index: 182568 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0487. Min Act: 0.0001

Data Index: 591046 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0471. Min Act: 0.0001

Data Index: 40515 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0438. Min Act: -0.0000

Data Index: 715653 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0478. Min Act: -0.0000

Data Index: 774565 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0471. Min Act: 0.0000

Data Index: 987440 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0446. Min Act: -0.0000

Data Index: 405432 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0432. Min Act: -0.0000

Data Index: 465964 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0407. Min Act: -0.0000

Data Index: 256155 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0426. Min Act: 0.0000

Data Index: 133533 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0409. Min Act: -0.0000

Data Index: 465940 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0407. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0420. Min Act: -0.0000

Data Index: 785443 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0394. Min Act: -0.0000

Data Index: 71902 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0420. Min Act: -0.0000

Data Index: 28976 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0402. Min Act: -0.0000

Data Index: 269186 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1165185 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0384. Min Act: -0.0000

Data Index: 45353 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1092611 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1570069 (Python Code)

Max Activating Token Index: 273