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

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

Neuron 1986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.9469. Min Act: -0.0000

Data Index: 1453432 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1544945 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.8113. Min Act: -0.0000

Data Index: 1611107 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.8504. Min Act: -0.0000

Data Index: 1549029 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.9184. Min Act: -0.0000

Data Index: 1652976 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1522621 (Python Code)

Max Activating Token Index: 346

Text #6

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4718. Min Act: -0.0000

Data Index: 1648481 (Python Code)

Max Activating Token Index: 913

Text #7

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1502783 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7647. Min Act: -0.0000

Data Index: 1280739 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7696. Min Act: -0.0000

Data Index: 1458554 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7168. Min Act: -0.0000

Data Index: 1573427 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1444120 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1641710 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1417104 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1655109 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1574401 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1502091 (Python Code)

Max Activating Token Index: 590

Text #17

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1402273 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1404895 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1624864 (Python Code)

Max Activating Token Index: 121