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

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

Neuron 4370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2571. Min Range: -1.2571

Max Act: 1.2571. Min Act: -0.0000

Data Index: 128634 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.2571. Min Range: -1.2571

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1269121 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9497. Min Act: -0.0001

Data Index: 963433 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.2571. Min Range: -1.2571

Max Act: 1.0468. Min Act: -0.0000

Data Index: 250449 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1483458 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9670. Min Act: -0.0000

Data Index: 743158 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 1.2571. Min Range: -1.2571

Max Act: 1.0047. Min Act: -0.0000

Data Index: 630904 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1494568 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1373190 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1470704 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1364329 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1502145 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1648194 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1634739 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1566619 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1409818 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1368153 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1581445 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1623024 (Python Code)

Max Activating Token Index: 400

Text #19

Max Range: 1.2571. Min Range: -1.2571

Max Act: 0.8864. Min Act: -0.0001

Data Index: 70698 (C4 (Web Text))

Max Activating Token Index: 917