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

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

Neuron 2650 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1116935 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1438156 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1132984 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.2104. Min Act: -0.0000

Data Index: 479982 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.1439. Min Act: -0.0000

Data Index: 960160 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9947. Min Act: -0.0000

Data Index: 964439 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0200. Min Act: -0.0000

Data Index: 331422 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0716. Min Act: -0.0000

Data Index: 212331 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1276379 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9415. Min Act: -0.0000

Data Index: 910515 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1066896 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9488. Min Act: -0.0000

Data Index: 755127 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0006. Min Act: -0.0000

Data Index: 657716 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1490199 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8573. Min Act: -0.0000

Data Index: 555895 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8771. Min Act: -0.0000

Data Index: 165096 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9262. Min Act: -0.0000

Data Index: 687241 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8493. Min Act: -0.0000

Data Index: 360132 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1055275 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1552536 (Python Code)

Max Activating Token Index: 755