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

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

Neuron 1606 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: 0.8635. Min Range: -0.8635

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1638868 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1419360 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1656587 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1503455 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1412489 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1559682 (Python Code)

Max Activating Token Index: 216

Text #6

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1386691 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1424917 (Python Code)

Max Activating Token Index: 953

Text #8

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1524121 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5700. Min Act: -0.0001

Data Index: 1450513 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1545014 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1390684 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5239. Min Act: -0.0001

Data Index: 1422436 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5351. Min Act: -0.0001

Data Index: 1365873 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.5131. Min Act: -0.0001

Data Index: 1479131 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1371834 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4431. Min Act: -0.0001

Data Index: 1425765 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1578882 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4914. Min Act: -0.0001

Data Index: 1639517 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.8635. Min Range: -0.8635

Max Act: 0.4983. Min Act: -0.0001

Data Index: 1530421 (Python Code)

Max Activating Token Index: 427