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

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

Neuron 3680 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1104. Min Act: -0.0000

Data Index: 486218 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1225757 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0840. Min Act: -0.0000

Data Index: 211836 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1345126 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1321162 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0695. Min Act: -0.0000

Data Index: 225209 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0795. Min Act: -0.0000

Data Index: 12213 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0679. Min Act: -0.0000

Data Index: 591211 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1319757 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1554152 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1056754 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0635. Min Act: -0.0000

Data Index: 662044 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0620. Min Act: -0.0000

Data Index: 498226 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0613. Min Act: -0.0000

Data Index: 656599 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0608. Min Act: -0.0000

Data Index: 185447 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0630. Min Act: -0.0000

Data Index: 815297 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0576. Min Act: -0.0000

Data Index: 524657 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1020781 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0598. Min Act: -0.0000

Data Index: 562050 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1013676 (C4 (Web Text))

Max Activating Token Index: 47