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

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

Neuron 1189 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: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0002

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0525. Min Act: -0.0002

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1285171 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0510. Min Act: -0.0001

Data Index: 780648 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0506. Min Act: -0.0002

Data Index: 17105 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1261206 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0463. Min Act: -0.0001

Data Index: 439428 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0457. Min Act: -0.0002

Data Index: 792833 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1263454 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0451. Min Act: -0.0001

Data Index: 603621 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0432. Min Act: -0.0002

Data Index: 648600 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0493. Min Act: -0.0002

Data Index: 740460 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0495. Min Act: -0.0002

Data Index: 704011 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0450. Min Act: -0.0002

Data Index: 434841 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1260658 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0462. Min Act: -0.0002

Data Index: 812946 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0442. Min Act: -0.0002

Data Index: 429856 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0420. Min Act: -0.0001

Data Index: 906888 (C4 (Web Text))

Max Activating Token Index: 338