Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 167 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1544561 (Python Code)

Max Activating Token Index: 340

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0627. Min Act: -0.0004

Data Index: 1462116 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1500260 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1577231 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1371285 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1477180 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1434257 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1426194 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1447363 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1448403 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0538. Min Act: -0.0003

Data Index: 811536 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0545. Min Act: -0.0004

Data Index: 1597484 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1608962 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1568254 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1431585 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1572814 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1363525 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1602200 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1637820 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0496. Min Act: -0.0004

Data Index: 1432740 (Python Code)

Max Activating Token Index: 956