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

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

Neuron 6060 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1363539 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.6014. Min Act: 0.0000

Data Index: 1490469 (Python Code)

Max Activating Token Index: 844

Text #2

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.2828. Min Act: -0.0000

Data Index: 1471919 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.0794. Min Act: -0.0000

Data Index: 1617698 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.1602. Min Act: 0.0000

Data Index: 1477961 (Python Code)

Max Activating Token Index: 433

Text #5

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9947. Min Act: -0.0000

Data Index: 1511013 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.1117. Min Act: 0.0000

Data Index: 1417924 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.8585. Min Act: -0.0000

Data Index: 1396248 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.7592. Min Act: -0.0000

Data Index: 1400210 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.7007. Min Act: -0.0000

Data Index: 1551103 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.7644. Min Act: -0.0000

Data Index: 1619692 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.5467. Min Act: -0.0000

Data Index: 1587739 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.5192. Min Act: -0.0000

Data Index: 1509276 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.6300. Min Act: -0.0000

Data Index: 1396274 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.5011. Min Act: -0.0000

Data Index: 1427259 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.4445. Min Act: -0.0000

Data Index: 1389146 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1523172 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.6630. Min Act: -0.0000

Data Index: 1379821 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.3673. Min Act: -0.0000

Data Index: 1079891 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.6202. Min Act: 0.0000

Data Index: 1514103 (Python Code)

Max Activating Token Index: 247