Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1269 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.4163. Min Act: -0.0001

Data Index: 57398 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2600. Min Act: -0.0001

Data Index: 1205152 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1476. Min Act: -0.0001

Data Index: 1105231 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2532. Min Act: -0.0001

Data Index: 914516 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1671. Min Act: -0.0001

Data Index: 786773 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1400. Min Act: -0.0001

Data Index: 686674 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0271. Min Act: -0.0001

Data Index: 821612 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1417. Min Act: -0.0001

Data Index: 1336423 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0026. Min Act: -0.0001

Data Index: 268060 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1685. Min Act: -0.0001

Data Index: 1033050 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9976. Min Act: -0.0001

Data Index: 243444 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1610. Min Act: -0.0001

Data Index: 32761 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0955. Min Act: -0.0001

Data Index: 1040647 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1170. Min Act: -0.0001

Data Index: 704853 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1107. Min Act: -0.0001

Data Index: 223656 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1336. Min Act: -0.0001

Data Index: 1241442 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0965. Min Act: -0.0001

Data Index: 1178737 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1281. Min Act: -0.0001

Data Index: 1035299 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1574. Min Act: -0.0001

Data Index: 882871 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0510. Min Act: -0.0001

Data Index: 217450 (C4 (Web Text))

Max Activating Token Index: 534