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

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

Neuron 1827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.4546. Min Act: -0.0000

Data Index: 147959 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.4321. Min Act: -0.0001

Data Index: 511024 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.4247. Min Act: -0.0000

Data Index: 668195 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1044041 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1088934 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1422. Min Act: -0.0000

Data Index: 545087 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3016. Min Act: -0.0000

Data Index: 960658 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2872. Min Act: -0.0000

Data Index: 656240 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1284733 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2692. Min Act: -0.0000

Data Index: 768164 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3459. Min Act: -0.0000

Data Index: 82503 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1152362 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0936. Min Act: -0.0000

Data Index: 262614 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1986. Min Act: -0.0000

Data Index: 437880 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1122897 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1081225 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3249. Min Act: -0.0001

Data Index: 236272 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0842. Min Act: -0.0000

Data Index: 697623 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1186251 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0834. Min Act: -0.0000

Data Index: 653162 (C4 (Web Text))

Max Activating Token Index: 192