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

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

Neuron 2078 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: 0.9405. Min Range: -0.9405

Max Act: 0.8831. Min Act: -0.0000

Data Index: 865587 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.9405. Min Act: -0.0000

Data Index: 613390 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7616. Min Act: -0.0000

Data Index: 560129 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7319. Min Act: -0.0000

Data Index: 218451 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1270284 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7258. Min Act: -0.0000

Data Index: 695082 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7004. Min Act: -0.0000

Data Index: 641266 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7469. Min Act: -0.0000

Data Index: 340458 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7090. Min Act: -0.0000

Data Index: 92050 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6962. Min Act: -0.0000

Data Index: 351496 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6857. Min Act: -0.0000

Data Index: 512305 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6829. Min Act: -0.0000

Data Index: 884772 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1345370 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6567. Min Act: -0.0000

Data Index: 167007 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1264352 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6715. Min Act: -0.0000

Data Index: 377638 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1257876 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7112. Min Act: -0.0000

Data Index: 20801 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1201812 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6627. Min Act: -0.0000

Data Index: 679987 (C4 (Web Text))

Max Activating Token Index: 30