Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4771 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0002

Data Index: 902564 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0820. Min Act: -0.0002

Data Index: 879023 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0641. Min Act: -0.0002

Data Index: 635573 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0643. Min Act: -0.0002

Data Index: 671552 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1121943 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1276487 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0663. Min Act: -0.0002

Data Index: 141376 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1133640 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0640. Min Act: -0.0002

Data Index: 709722 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0559. Min Act: -0.0002

Data Index: 783263 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0589. Min Act: -0.0002

Data Index: 429247 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0682. Min Act: -0.0002

Data Index: 630454 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0569. Min Act: -0.0002

Data Index: 334197 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0568. Min Act: -0.0002

Data Index: 632801 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0536. Min Act: -0.0002

Data Index: 140111 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0630. Min Act: -0.0002

Data Index: 297611 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0573. Min Act: -0.0002

Data Index: 851527 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0643. Min Act: -0.0002

Data Index: 194791 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1195488 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0576. Min Act: -0.0002

Data Index: 256241 (C4 (Web Text))

Max Activating Token Index: 704