Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2489 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.6974. Min Act: -0.0000

Data Index: 1302320 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4332. Min Act: -0.0000

Data Index: 359916 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3968. Min Act: -0.0000

Data Index: 252579 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4407. Min Act: -0.0000

Data Index: 631178 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4134. Min Act: -0.0000

Data Index: 1193353 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1067021 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2288. Min Act: -0.0000

Data Index: 592573 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2171. Min Act: -0.0001

Data Index: 279913 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1367. Min Act: -0.0000

Data Index: 489467 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1125. Min Act: -0.0001

Data Index: 1277240 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1677. Min Act: -0.0000

Data Index: 230963 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1157700 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1215. Min Act: -0.0001

Data Index: 1229339 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2976. Min Act: -0.0001

Data Index: 11168 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1253176 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0211. Min Act: -0.0000

Data Index: 101279 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0833. Min Act: -0.0000

Data Index: 591932 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0869. Min Act: -0.0000

Data Index: 827942 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0821. Min Act: -0.0000

Data Index: 636825 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0575. Min Act: -0.0000

Data Index: 722307 (C4 (Web Text))

Max Activating Token Index: 7