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

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

Neuron 4106 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5963. Min Range: -2.5963

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1254659 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 2.5963. Min Range: -2.5963

Max Act: 2.2438. Min Act: -0.0000

Data Index: 101817 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.5963. Min Range: -2.5963

Max Act: 2.3721. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 2.5963. Min Range: -2.5963

Max Act: 2.2116. Min Act: -0.0000

Data Index: 51521 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 2.5963. Min Range: -2.5963

Max Act: 2.1877. Min Act: -0.0000

Data Index: 1260738 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.9983. Min Act: -0.0000

Data Index: 1486742 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.9770. Min Act: -0.0000

Data Index: 1008460 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.9677. Min Act: -0.0000

Data Index: 456518 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.8715. Min Act: -0.0000

Data Index: 1367386 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1622909 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1523236 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1136425 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1443815 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.5893. Min Act: -0.0000

Data Index: 826284 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1045138 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1562919 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.6550. Min Act: -0.0000

Data Index: 901372 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1404172 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.6117. Min Act: -0.0000

Data Index: 838003 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.5963. Min Range: -2.5963

Max Act: 1.5433. Min Act: -0.0000

Data Index: 1461784 (Python Code)

Max Activating Token Index: 558