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

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

Neuron 4555 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: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0002

Data Index: 593111 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0115. Min Act: -0.0002

Data Index: 653581 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0127. Min Act: -0.0002

Data Index: 126902 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0128. Min Act: -0.0002

Data Index: 388291 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0115. Min Act: -0.0002

Data Index: 546222 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0116. Min Act: -0.0002

Data Index: 107936 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0002

Data Index: 298564 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0002

Data Index: 335526 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1563337 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1442650 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0127. Min Act: -0.0002

Data Index: 675071 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0102. Min Act: -0.0002

Data Index: 216086 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1007230 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1001949 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0101. Min Act: -0.0002

Data Index: 938853 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1439874 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0105. Min Act: -0.0002

Data Index: 110015 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0088. Min Act: -0.0002

Data Index: 591526 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0108. Min Act: -0.0002

Data Index: 16653 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0002

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 856