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

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

Neuron 2977 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1097877 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1423139 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4224. Min Act: -0.0001

Data Index: 462578 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4056. Min Act: -0.0000

Data Index: 940268 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1157260 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4089. Min Act: -0.0001

Data Index: 842466 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3701. Min Act: -0.0001

Data Index: 1654129 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1475533 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1564107 (Python Code)

Max Activating Token Index: 159

Text #9

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4135. Min Act: -0.0001

Data Index: 914279 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1537371 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1452561 (Python Code)

Max Activating Token Index: 938

Text #12

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1592334 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4106. Min Act: -0.0001

Data Index: 1433689 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1645468 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3444. Min Act: -0.0001

Data Index: 464344 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1522937 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1495739 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1411344 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3955. Min Act: -0.0001

Data Index: 1528039 (Python Code)

Max Activating Token Index: 611