Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3962 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6590. Min Act: -0.0001

Data Index: 1269769 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1620726 (Python Code)

Max Activating Token Index: 707

Text #2

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5947. Min Act: -0.0001

Data Index: 1591366 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5431. Min Act: -0.0001

Data Index: 1038435 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1608761 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5385. Min Act: -0.0001

Data Index: 1574357 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1284661 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1644189 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4734. Min Act: -0.0001

Data Index: 1421232 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4998. Min Act: -0.0001

Data Index: 1649550 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4668. Min Act: -0.0001

Data Index: 617904 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5152. Min Act: -0.0001

Data Index: 1444641 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1423672 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1479431 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4537. Min Act: -0.0001

Data Index: 1473290 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4266. Min Act: -0.0001

Data Index: 517494 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4531. Min Act: -0.0001

Data Index: 363802 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4718. Min Act: -0.0001

Data Index: 1653211 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4640. Min Act: -0.0001

Data Index: 1492259 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1199154 (C4 (Web Text))

Max Activating Token Index: 586