Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2018 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1038431 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1247396 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0634. Min Act: -0.0002

Data Index: 870702 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0616. Min Act: -0.0002

Data Index: 722391 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0633. Min Act: -0.0002

Data Index: 573536 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0604. Min Act: -0.0002

Data Index: 279633 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1056628 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0621. Min Act: -0.0002

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1191328 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0594. Min Act: -0.0002

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1359778 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0609. Min Act: -0.0002

Data Index: 236255 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0600. Min Act: -0.0002

Data Index: 632865 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1072592 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0603. Min Act: -0.0002

Data Index: 302248 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0575. Min Act: -0.0002

Data Index: 302115 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0566. Min Act: -0.0002

Data Index: 531132 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1143532 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0618. Min Act: -0.0002

Data Index: 148123 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1106303 (C4 (Web Text))

Max Activating Token Index: 834