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

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

Neuron 2111 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8786. Min Act: -0.0000

Data Index: 1385194 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8652. Min Act: -0.0000

Data Index: 1477357 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1584399 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7319. Min Act: -0.0000

Data Index: 1633154 (Python Code)

Max Activating Token Index: 925

Text #4

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6022. Min Act: -0.0000

Data Index: 1610737 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1652741 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1408585 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1417752 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1448179 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1553597 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1624767 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1502319 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1452094 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1378383 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1436578 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1502407 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1414807 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1459406 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1560725 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1511712 (Python Code)

Max Activating Token Index: 166