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

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

Neuron 5110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0000

Data Index: 343777 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0667. Min Act: -0.0000

Data Index: 379251 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0671. Min Act: -0.0000

Data Index: 483435 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1344589 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0640. Min Act: -0.0000

Data Index: 295272 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0675. Min Act: -0.0000

Data Index: 339034 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1083792 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1191431 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0623. Min Act: -0.0000

Data Index: 560415 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0624. Min Act: -0.0000

Data Index: 202249 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0637. Min Act: -0.0000

Data Index: 110415 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1105024 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0588. Min Act: -0.0000

Data Index: 402624 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1087706 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0602. Min Act: -0.0000

Data Index: 693901 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0624. Min Act: -0.0000

Data Index: 198273 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0591. Min Act: -0.0000

Data Index: 373127 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0589. Min Act: -0.0000

Data Index: 115173 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0584. Min Act: -0.0000

Data Index: 378524 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1158033 (C4 (Web Text))

Max Activating Token Index: 690