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

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

Neuron 2589 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: 1.2369. Min Range: -1.2369

Max Act: 1.2168. Min Act: -0.0001

Data Index: 1063730 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1732. Min Act: -0.0001

Data Index: 693973 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.2369. Min Act: -0.0001

Data Index: 1100024 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.2261. Min Act: -0.0001

Data Index: 566210 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1901. Min Act: -0.0001

Data Index: 872239 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1638. Min Act: -0.0001

Data Index: 1034799 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1883. Min Act: -0.0001

Data Index: 1110901 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1077. Min Act: -0.0001

Data Index: 278182 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1497. Min Act: -0.0001

Data Index: 1205282 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1065469 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0862. Min Act: -0.0001

Data Index: 916539 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.1409. Min Act: -0.0001

Data Index: 100906 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0930. Min Act: -0.0001

Data Index: 824343 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0842. Min Act: -0.0001

Data Index: 1160919 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0528. Min Act: -0.0001

Data Index: 267974 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0385. Min Act: -0.0001

Data Index: 1165287 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0184. Min Act: -0.0001

Data Index: 236579 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0576. Min Act: -0.0001

Data Index: 540703 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0228. Min Act: -0.0001

Data Index: 263370 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.2369. Min Range: -1.2369

Max Act: 1.0745. Min Act: -0.0001

Data Index: 558559 (C4 (Web Text))

Max Activating Token Index: 59