Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1452865 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1528806 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1463781 (Python Code)

Max Activating Token Index: 614

Text #3

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1639034 (Python Code)

Max Activating Token Index: 915

Text #4

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1657040 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1404648 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1440818 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1542539 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1452349 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1636952 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1454251 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1635938 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1586200 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1405494 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1452446 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3391. Min Act: -0.0001

Data Index: 1521463 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1526581 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1421533 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1435540 (Python Code)

Max Activating Token Index: 930

Text #19

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1415577 (Python Code)

Max Activating Token Index: 753