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

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

Neuron 164 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: 1.4261. Min Range: -1.4261

Max Act: 1.4261. Min Act: -0.0000

Data Index: 958106 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1121979 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2073. Min Act: -0.0000

Data Index: 824232 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1512. Min Act: -0.0000

Data Index: 256733 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1691. Min Act: -0.0000

Data Index: 853791 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0693. Min Act: -0.0000

Data Index: 421097 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1129413 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1337415 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0454. Min Act: -0.0000

Data Index: 143338 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9630. Min Act: -0.0000

Data Index: 136568 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1195. Min Act: -0.0000

Data Index: 704343 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0345. Min Act: -0.0000

Data Index: 660695 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9787. Min Act: -0.0000

Data Index: 644041 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0413. Min Act: -0.0000

Data Index: 732629 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0254. Min Act: -0.0000

Data Index: 754595 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9855. Min Act: -0.0000

Data Index: 84031 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1278852 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1172360 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9488. Min Act: -0.0000

Data Index: 775265 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9156. Min Act: -0.0000

Data Index: 659457 (C4 (Web Text))

Max Activating Token Index: 655