Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2336 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.3772. Min Act: -0.0001

Data Index: 357004 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1974. Min Act: -0.0001

Data Index: 646268 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.2020. Min Act: -0.0002

Data Index: 13294 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1661. Min Act: -0.0001

Data Index: 1141065 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1088. Min Act: -0.0001

Data Index: 1317342 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1403. Min Act: -0.0001

Data Index: 1000619 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1186. Min Act: -0.0001

Data Index: 167547 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1164224 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0504. Min Act: -0.0001

Data Index: 706788 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0785. Min Act: -0.0001

Data Index: 496446 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0485. Min Act: -0.0002

Data Index: 333381 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1107. Min Act: -0.0002

Data Index: 1187983 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.3772. Min Range: -1.3772

Max Act: 0.9765. Min Act: -0.0001

Data Index: 368524 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0658. Min Act: -0.0002

Data Index: 781936 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0970. Min Act: -0.0002

Data Index: 448196 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0842. Min Act: -0.0001

Data Index: 515119 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0031. Min Act: -0.0001

Data Index: 656112 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0764. Min Act: -0.0001

Data Index: 632515 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1223. Min Act: -0.0002

Data Index: 13588 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0023. Min Act: -0.0001

Data Index: 952076 (C4 (Web Text))

Max Activating Token Index: 873