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

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

Neuron 4425 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7020. Min Act: -0.0000

Data Index: 805558 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7886. Min Act: -0.0000

Data Index: 58568 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 64485 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8455. Min Act: -0.0000

Data Index: 801683 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8168. Min Act: -0.0000

Data Index: 736967 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8346. Min Act: -0.0000

Data Index: 608550 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1075880 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7601. Min Act: -0.0000

Data Index: 477187 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1051757 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7354. Min Act: -0.0000

Data Index: 892908 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1181648 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6999. Min Act: -0.0000

Data Index: 388298 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7157. Min Act: -0.0000

Data Index: 862712 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1111245 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6938. Min Act: -0.0000

Data Index: 79583 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1117052 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1338449 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6816. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6781. Min Act: -0.0000

Data Index: 336337 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1067261 (C4 (Web Text))

Max Activating Token Index: 278