Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1750 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4258. Min Act: -0.0001

Data Index: 105667 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1264875 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4046. Min Act: -0.0001

Data Index: 488557 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4225. Min Act: -0.0001

Data Index: 998658 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4304. Min Act: -0.0001

Data Index: 269588 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4169. Min Act: -0.0001

Data Index: 314525 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3992. Min Act: -0.0001

Data Index: 634670 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3544. Min Act: -0.0001

Data Index: 1219692 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3827. Min Act: -0.0001

Data Index: 159223 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1165366 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1314462 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3599. Min Act: -0.0001

Data Index: 1196897 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3578. Min Act: -0.0001

Data Index: 1226064 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1196284 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3635. Min Act: -0.0001

Data Index: 749908 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3479. Min Act: -0.0001

Data Index: 375197 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3829. Min Act: -0.0001

Data Index: 351757 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3415. Min Act: -0.0001

Data Index: 380436 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3678. Min Act: -0.0001

Data Index: 1300747 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3548. Min Act: -0.0001

Data Index: 1126441 (C4 (Web Text))

Max Activating Token Index: 293