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

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

Neuron 5370 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1101708 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1212814 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0618. Min Act: -0.0001

Data Index: 17908 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1163570 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1471384 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0627. Min Act: -0.0001

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0597. Min Act: -0.0001

Data Index: 312655 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0588. Min Act: -0.0001

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0517. Min Act: -0.0001

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0592. Min Act: -0.0001

Data Index: 689217 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1228687 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0598. Min Act: -0.0001

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1030979 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0563. Min Act: -0.0001

Data Index: 597542 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0557. Min Act: -0.0001

Data Index: 883246 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0543. Min Act: -0.0001

Data Index: 370875 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0523. Min Act: -0.0001

Data Index: 894864 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1277693 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1647682 (Python Code)

Max Activating Token Index: 938