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

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

Neuron 138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2472. Min Act: -0.0001

Data Index: 141187 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2361. Min Act: -0.0001

Data Index: 980224 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2017. Min Act: -0.0001

Data Index: 583462 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2239. Min Act: -0.0001

Data Index: 556972 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1187068 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1889. Min Act: -0.0001

Data Index: 449782 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1785. Min Act: -0.0001

Data Index: 353285 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1147885 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1731. Min Act: -0.0001

Data Index: 397160 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1660. Min Act: -0.0001

Data Index: 829583 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1636. Min Act: -0.0001

Data Index: 291568 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1067820 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1540. Min Act: -0.0001

Data Index: 919779 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1672. Min Act: -0.0001

Data Index: 707882 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1609. Min Act: -0.0001

Data Index: 463589 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1038321 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1635. Min Act: -0.0001

Data Index: 588839 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1773. Min Act: -0.0001

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 340