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

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

Neuron 4162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1590711 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.6959. Min Act: -0.0000

Data Index: 1605297 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1599315 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1645663 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1643354 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1530254 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1645909 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1415109 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1535824 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1396285 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1507130 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1379230 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1475416 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1639464 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1528401 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1522116 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1440106 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1619454 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.2374. Min Act: -0.0000

Data Index: 412686 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1506304 (Python Code)

Max Activating Token Index: 802