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

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

Neuron 2361 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7672. Min Range: -4.7672

Max Act: 4.7672. Min Act: -0.0000

Data Index: 13108 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.8914. Min Act: -0.0000

Data Index: 206367 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.6293. Min Act: -0.0000

Data Index: 20236 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.2419. Min Act: -0.0000

Data Index: 305688 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.0133. Min Act: -0.0000

Data Index: 615022 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.0582. Min Act: -0.0000

Data Index: 1465783 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8746. Min Act: -0.0000

Data Index: 1624045 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.9514. Min Act: -0.0000

Data Index: 583290 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.9119. Min Act: -0.0000

Data Index: 462 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8838. Min Act: -0.0000

Data Index: 1492145 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8774. Min Act: -0.0000

Data Index: 1411073 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8557. Min Act: -0.0000

Data Index: 174248 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.7001. Min Act: -0.0000

Data Index: 150657 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8378. Min Act: -0.0000

Data Index: 1598398 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8571. Min Act: -0.0000

Data Index: 119877 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.7881. Min Act: -0.0000

Data Index: 685960 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.7762. Min Act: -0.0000

Data Index: 153057 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.8993. Min Act: -0.0000

Data Index: 859672 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 4.7672. Min Range: -4.7672

Max Act: 2.7153. Min Act: -0.0000

Data Index: 1636371 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 4.7672. Min Range: -4.7672

Max Act: 3.0615. Min Act: -0.0000

Data Index: 628130 (C4 (Web Text))

Max Activating Token Index: 921