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

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

Neuron 1257 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: 0.1431. Min Range: -0.1431

Max Act: 0.1431. Min Act: -0.0001

Data Index: 114071 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1471564 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1306. Min Act: -0.0001

Data Index: 990713 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1410787 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1164239 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1285. Min Act: -0.0001

Data Index: 224373 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1655096 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1097. Min Act: -0.0001

Data Index: 206302 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1264. Min Act: -0.0001

Data Index: 910449 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1374639 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1133. Min Act: -0.0000

Data Index: 808692 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1204. Min Act: -0.0001

Data Index: 754373 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1368646 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1450842 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1148537 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1283890 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1003. Min Act: -0.0001

Data Index: 692298 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1172. Min Act: -0.0001

Data Index: 595105 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1490559 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1050562 (C4 (Web Text))

Max Activating Token Index: 800