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

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

Neuron 1406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.3649. Min Act: -0.0001

Data Index: 261255 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2953. Min Act: -0.0001

Data Index: 808007 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.5112. Min Act: -0.0001

Data Index: 437404 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.3059. Min Act: -0.0001

Data Index: 510159 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.4080. Min Act: -0.0001

Data Index: 697264 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2985. Min Act: -0.0001

Data Index: 299338 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.3208. Min Act: -0.0001

Data Index: 648558 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1692. Min Act: -0.0001

Data Index: 761980 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2359. Min Act: -0.0001

Data Index: 1151510 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2352. Min Act: -0.0001

Data Index: 250243 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0775. Min Act: -0.0001

Data Index: 384504 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1768. Min Act: -0.0001

Data Index: 142985 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2159. Min Act: -0.0001

Data Index: 353844 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1484. Min Act: -0.0001

Data Index: 824210 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1123. Min Act: -0.0001

Data Index: 169370 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1553. Min Act: -0.0001

Data Index: 939497 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1133. Min Act: -0.0001

Data Index: 820422 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1522. Min Act: -0.0001

Data Index: 728010 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0494. Min Act: -0.0001

Data Index: 430820 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0804. Min Act: -0.0001

Data Index: 379776 (C4 (Web Text))

Max Activating Token Index: 366