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

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

Neuron 2724 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: 3.7365. Min Range: -3.7365

Max Act: 3.2707. Min Act: -0.0001

Data Index: 703823 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.7365. Min Range: -3.7365

Max Act: 3.7365. Min Act: -0.0000

Data Index: 10430 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.7365. Min Range: -3.7365

Max Act: 3.2051. Min Act: -0.0000

Data Index: 254637 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 3.7365. Min Range: -3.7365

Max Act: 3.1920. Min Act: -0.0000

Data Index: 1548790 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 3.7365. Min Range: -3.7365

Max Act: 3.4152. Min Act: -0.0000

Data Index: 1570212 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.9327. Min Act: -0.0000

Data Index: 1525002 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.6896. Min Act: -0.0000

Data Index: 1636154 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.6159. Min Act: -0.0000

Data Index: 323815 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.5639. Min Act: -0.0000

Data Index: 367763 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.8177. Min Act: -0.0001

Data Index: 782486 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.7890. Min Act: -0.0000

Data Index: 319477 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.3924. Min Act: -0.0000

Data Index: 311895 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.5910. Min Act: -0.0000

Data Index: 83692 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.6921. Min Act: -0.0000

Data Index: 610767 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.6747. Min Act: -0.0000

Data Index: 549555 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.6730. Min Act: -0.0000

Data Index: 1157583 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.1973. Min Act: -0.0000

Data Index: 1162194 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.4897. Min Act: -0.0000

Data Index: 1580118 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.1365. Min Act: -0.0000

Data Index: 820391 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 3.7365. Min Range: -3.7365

Max Act: 2.4800. Min Act: -0.0000

Data Index: 790440 (C4 (Web Text))

Max Activating Token Index: 274