Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 49 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0004

Data Index: 634378 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0646. Min Act: -0.0004

Data Index: 881329 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0589. Min Act: -0.0004

Data Index: 726243 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0620. Min Act: -0.0004

Data Index: 723191 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0588. Min Act: -0.0004

Data Index: 777688 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0689. Min Act: -0.0004

Data Index: 365133 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1184554 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0603. Min Act: -0.0004

Data Index: 62009 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0648. Min Act: -0.0004

Data Index: 1041239 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0616. Min Act: -0.0004

Data Index: 48677 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0499. Min Act: -0.0004

Data Index: 117566 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0565. Min Act: -0.0004

Data Index: 187380 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0561. Min Act: -0.0004

Data Index: 7561 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0536. Min Act: -0.0004

Data Index: 409477 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0581. Min Act: -0.0004

Data Index: 271796 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0553. Min Act: -0.0004

Data Index: 903599 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0528. Min Act: -0.0004

Data Index: 1106447 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0536. Min Act: -0.0004

Data Index: 493621 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0536. Min Act: -0.0004

Data Index: 739081 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0512. Min Act: -0.0004

Data Index: 1142279 (C4 (Web Text))

Max Activating Token Index: 305