Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2214 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.6964. Min Act: -0.0000

Data Index: 1526637 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.4072. Min Act: -0.0000

Data Index: 1606455 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.3306. Min Act: -0.0000

Data Index: 1543862 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.2981. Min Act: -0.0000

Data Index: 1593441 (Python Code)

Max Activating Token Index: 152

Text #4

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.4703. Min Act: -0.0000

Data Index: 1587265 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1390521 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.2992. Min Act: -0.0000

Data Index: 1408545 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.0411. Min Act: -0.0000

Data Index: 1482699 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.1307. Min Act: -0.0000

Data Index: 1528322 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.2304. Min Act: -0.0000

Data Index: 1463322 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.2123. Min Act: -0.0000

Data Index: 1614219 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.0714. Min Act: -0.0000

Data Index: 1436798 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.1937. Min Act: -0.0000

Data Index: 1449961 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.1925. Min Act: -0.0000

Data Index: 1514586 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1580267 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1550642 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.2858. Min Act: -0.0000

Data Index: 1383768 (Python Code)

Max Activating Token Index: 790

Text #17

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.1701. Min Act: -0.0000

Data Index: 1561595 (Python Code)

Max Activating Token Index: 939

Text #18

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.0463. Min Act: -0.0000

Data Index: 1459413 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 2.6964. Min Range: -2.6964

Max Act: 2.0434. Min Act: -0.0000

Data Index: 1573953 (Python Code)

Max Activating Token Index: 569