Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.4575. Min Act: -0.0001

Data Index: 463598 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.9605. Min Act: -0.0000

Data Index: 103177 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.2813. Min Act: -0.0001

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.2795. Min Act: -0.0001

Data Index: 699700 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.2944. Min Act: -0.0000

Data Index: 580341 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.0389. Min Act: -0.0001

Data Index: 450718 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.9944. Min Act: -0.0000

Data Index: 610134 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.1035. Min Act: -0.0000

Data Index: 536137 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.8148. Min Act: -0.0000

Data Index: 651122 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.1815. Min Act: -0.0001

Data Index: 1217451 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.9554. Min Act: -0.0000

Data Index: 329888 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.4575. Min Range: -2.4575

Max Act: 2.1061. Min Act: -0.0000

Data Index: 645090 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1284658 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.7199. Min Act: -0.0000

Data Index: 388605 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.6129. Min Act: -0.0001

Data Index: 393136 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.6856. Min Act: -0.0001

Data Index: 172217 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.7596. Min Act: -0.0000

Data Index: 29676 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.9716. Min Act: -0.0000

Data Index: 840303 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.9392. Min Act: -0.0000

Data Index: 106668 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.4575. Min Range: -2.4575

Max Act: 1.6985. Min Act: -0.0000

Data Index: 1156753 (C4 (Web Text))

Max Activating Token Index: 202