Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1636089 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1481825 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1605355 (Python Code)

Max Activating Token Index: 659

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1535935 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1567221 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1373708 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1383223 (Python Code)

Max Activating Token Index: 965

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1403541 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0536. Min Act: -0.0004

Data Index: 1601661 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1540919 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1596438 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1558245 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1404408 (Python Code)

Max Activating Token Index: 552

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1618982 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1616389 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0525. Min Act: -0.0004

Data Index: 1610165 (Python Code)

Max Activating Token Index: 583

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1420102 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0004

Data Index: 1610585 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1518343 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1629029 (Python Code)

Max Activating Token Index: 81