Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2578 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.4717. Min Act: -0.0000

Data Index: 570178 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.3407. Min Act: -0.0000

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.1202. Min Act: -0.0000

Data Index: 1055947 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0820. Min Act: -0.0000

Data Index: 1206469 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.1047. Min Act: -0.0000

Data Index: 1059311 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.2641. Min Act: -0.0000

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0824. Min Act: -0.0000

Data Index: 719721 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0605. Min Act: -0.0000

Data Index: 87743 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0008. Min Act: -0.0000

Data Index: 1244837 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9938. Min Act: -0.0000

Data Index: 577433 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9914. Min Act: -0.0000

Data Index: 508 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0020. Min Act: -0.0000

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9273. Min Act: -0.0000

Data Index: 105691 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9107. Min Act: -0.0000

Data Index: 1156558 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.8585. Min Act: -0.0000

Data Index: 748394 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.5564. Min Act: -0.0000

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9668. Min Act: -0.0000

Data Index: 908667 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0020. Min Act: -0.0000

Data Index: 934087 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9718. Min Act: -0.0000

Data Index: 1152128 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.6305. Min Act: 0.0000

Data Index: 573486 (C4 (Web Text))

Max Activating Token Index: 265