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

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

Neuron 649 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: 1.5663. Min Range: -1.5663

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1554645 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1607567 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1466783 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1593157 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2221. Min Act: -0.0000

Data Index: 1441998 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1473027 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1646130 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1457254 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1498463 (Python Code)

Max Activating Token Index: 360

Text #9

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1500368 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1522583 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1593088 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1373396 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0572. Min Act: -0.0000

Data Index: 691956 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1652949 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1432151 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1511903 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1482436 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1529452 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1539007 (Python Code)

Max Activating Token Index: 751