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

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

Neuron 2199 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5640. Min Act: -0.0003

Data Index: 384212 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5833. Min Act: -0.0003

Data Index: 1212379 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4961. Min Act: -0.0003

Data Index: 955214 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5570. Min Act: -0.0003

Data Index: 1392396 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5146. Min Act: -0.0003

Data Index: 1448860 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5405. Min Act: -0.0003

Data Index: 1196989 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5460. Min Act: -0.0003

Data Index: 541116 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4522. Min Act: -0.0003

Data Index: 1499545 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4974. Min Act: -0.0003

Data Index: 1474747 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4736. Min Act: -0.0003

Data Index: 1187650 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4841. Min Act: -0.0003

Data Index: 440582 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4788. Min Act: -0.0003

Data Index: 1512766 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4771. Min Act: -0.0003

Data Index: 1424778 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4629. Min Act: -0.0003

Data Index: 954198 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4710. Min Act: -0.0003

Data Index: 704351 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4570. Min Act: -0.0003

Data Index: 585936 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3628. Min Act: -0.0003

Data Index: 1567604 (Python Code)

Max Activating Token Index: 848

Text #17

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4664. Min Act: -0.0003

Data Index: 1420062 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4665. Min Act: -0.0003

Data Index: 1538585 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4707. Min Act: -0.0003

Data Index: 1364953 (Python Code)

Max Activating Token Index: 243