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

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

Neuron 365 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4682. Min Range: -2.4682

Max Act: 2.4682. Min Act: -0.0000

Data Index: 1011479 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.4682. Min Range: -2.4682

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1131241 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.4682. Min Range: -2.4682

Max Act: 2.1949. Min Act: -0.0000

Data Index: 1244690 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.9906. Min Act: -0.0000

Data Index: 304616 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.8386. Min Act: -0.0000

Data Index: 748708 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.7943. Min Act: -0.0000

Data Index: 767925 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.7836. Min Act: -0.0000

Data Index: 147331 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4927. Min Act: -0.0000

Data Index: 726842 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4881. Min Act: -0.0000

Data Index: 948198 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1354163 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.5237. Min Act: -0.0000

Data Index: 913179 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1128181 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.3755. Min Act: -0.0000

Data Index: 989124 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4558. Min Act: -0.0000

Data Index: 202536 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4365. Min Act: -0.0000

Data Index: 122849 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4277. Min Act: -0.0000

Data Index: 814077 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4811. Min Act: -0.0000

Data Index: 174198 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1089540 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.2972. Min Act: -0.0000

Data Index: 13141 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.4682. Min Range: -2.4682

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1240354 (C4 (Web Text))

Max Activating Token Index: 306