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

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

Neuron 4762 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: 1.7069. Min Range: -1.7069

Max Act: 1.7069. Min Act: -0.0000

Data Index: 700748 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.1574. Min Act: -0.0000

Data Index: 440206 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1017964 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0861. Min Act: -0.0000

Data Index: 938150 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0836. Min Act: -0.0000

Data Index: 382881 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0249. Min Act: -0.0001

Data Index: 452883 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0275. Min Act: -0.0000

Data Index: 952192 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9563. Min Act: -0.0000

Data Index: 789749 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1001811 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0033. Min Act: -0.0000

Data Index: 878140 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1172176 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9304. Min Act: -0.0000

Data Index: 447788 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.7069. Min Range: -1.7069

Max Act: 1.0228. Min Act: -0.0001

Data Index: 33375 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1175627 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9112. Min Act: -0.0000

Data Index: 27393 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.9100. Min Act: -0.0000

Data Index: 602847 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.8731. Min Act: -0.0001

Data Index: 730835 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.8647. Min Act: -0.0000

Data Index: 821115 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1080439 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.7069. Min Range: -1.7069

Max Act: 0.8837. Min Act: -0.0000

Data Index: 749683 (C4 (Web Text))

Max Activating Token Index: 506