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

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

Neuron 4380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1775. Min Act: -0.0001

Data Index: 94343 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1114776 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1243389 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1191. Min Act: -0.0000

Data Index: 684392 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1039. Min Act: -0.0001

Data Index: 700202 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1079. Min Act: -0.0001

Data Index: 568479 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1022. Min Act: -0.0001

Data Index: 366897 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1100. Min Act: -0.0000

Data Index: 774834 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1044. Min Act: -0.0001

Data Index: 324895 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0977. Min Act: -0.0001

Data Index: 903921 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1015. Min Act: -0.0001

Data Index: 225767 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1043. Min Act: -0.0001

Data Index: 466470 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1036. Min Act: -0.0001

Data Index: 906599 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1103552 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0944. Min Act: -0.0001

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1015. Min Act: -0.0001

Data Index: 905282 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0913. Min Act: -0.0001

Data Index: 88753 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0982. Min Act: -0.0001

Data Index: 620070 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0971. Min Act: -0.0001

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.0942. Min Act: -0.0001

Data Index: 648981 (C4 (Web Text))

Max Activating Token Index: 785