Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1066 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0006

Data Index: 782534 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0503. Min Act: -0.0006

Data Index: 190023 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0455. Min Act: -0.0006

Data Index: 650151 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0457. Min Act: -0.0006

Data Index: 179368 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0418. Min Act: -0.0006

Data Index: 39157 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0436. Min Act: -0.0006

Data Index: 1092166 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0415. Min Act: -0.0006

Data Index: 198684 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1164825 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1255525 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1029603 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0400. Min Act: -0.0006

Data Index: 174826 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0418. Min Act: -0.0006

Data Index: 797231 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1034845 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0402. Min Act: -0.0006

Data Index: 324938 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0386. Min Act: -0.0006

Data Index: 751033 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0386. Min Act: -0.0006

Data Index: 307048 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0401. Min Act: -0.0006

Data Index: 397799 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1251376 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0398. Min Act: -0.0006

Data Index: 701488 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0393. Min Act: -0.0006

Data Index: 534476 (C4 (Web Text))

Max Activating Token Index: 550