Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0000

Data Index: 851706 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8451. Min Act: -0.0001

Data Index: 264549 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8642. Min Act: -0.0001

Data Index: 832690 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1250923 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8601. Min Act: -0.0001

Data Index: 1283786 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9005. Min Act: -0.0001

Data Index: 488055 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1136187 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7906. Min Act: -0.0001

Data Index: 65125 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8087. Min Act: -0.0001

Data Index: 385477 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7893. Min Act: -0.0001

Data Index: 315194 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8446. Min Act: -0.0001

Data Index: 948320 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8107. Min Act: -0.0000

Data Index: 522631 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7295. Min Act: -0.0001

Data Index: 1332927 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7505. Min Act: -0.0001

Data Index: 557020 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7153. Min Act: -0.0001

Data Index: 459335 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7157. Min Act: -0.0001

Data Index: 990605 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7334. Min Act: -0.0000

Data Index: 765118 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7023. Min Act: -0.0001

Data Index: 120623 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.6827. Min Act: -0.0001

Data Index: 718282 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7208. Min Act: -0.0000

Data Index: 10987 (C4 (Web Text))

Max Activating Token Index: 130