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

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

Neuron 324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0001

Data Index: 862698 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1420. Min Act: -0.0001

Data Index: 470597 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1201. Min Act: -0.0001

Data Index: 896047 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1201. Min Act: -0.0001

Data Index: 80374 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1178. Min Act: -0.0001

Data Index: 741956 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1212. Min Act: -0.0001

Data Index: 381642 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1286. Min Act: -0.0001

Data Index: 93869 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.0972. Min Act: -0.0001

Data Index: 461086 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1219. Min Act: -0.0001

Data Index: 755623 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1063267 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1203520 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1091. Min Act: -0.0001

Data Index: 137392 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.0954. Min Act: -0.0001

Data Index: 743274 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.0973. Min Act: -0.0001

Data Index: 156345 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1108. Min Act: -0.0001

Data Index: 427051 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.0854. Min Act: -0.0001

Data Index: 425239 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1138. Min Act: -0.0001

Data Index: 955003 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1084. Min Act: -0.0001

Data Index: 64169 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1163359 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1043. Min Act: -0.0001

Data Index: 515130 (C4 (Web Text))

Max Activating Token Index: 950