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

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

Neuron 831 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: 1.1327. Min Range: -1.1327

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1628956 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 1.1327. Min Range: -1.1327

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1484425 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 1.1327. Min Range: -1.1327

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1385269 (Python Code)

Max Activating Token Index: 297

Text #3

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1641212 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 1.1327. Min Range: -1.1327

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1552200 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1594468 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1558479 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1655073 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1596476 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1369007 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1607408 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1643692 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1558752 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1545118 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1408392 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1550193 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1547488 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1364851 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1640783 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1425807 (Python Code)

Max Activating Token Index: 458