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

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

Neuron 3812 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: 0.1904. Min Range: -0.1904

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1215125 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1059289 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1324316 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1388. Min Act: -0.0001

Data Index: 688905 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1421. Min Act: -0.0001

Data Index: 739004 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1328. Min Act: -0.0001

Data Index: 844739 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1282. Min Act: -0.0001

Data Index: 529529 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1299. Min Act: -0.0001

Data Index: 359558 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1022985 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1298. Min Act: -0.0001

Data Index: 205988 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1340465 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1330. Min Act: -0.0001

Data Index: 160719 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1285. Min Act: -0.0001

Data Index: 948693 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1199. Min Act: -0.0001

Data Index: 344125 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1211. Min Act: -0.0001

Data Index: 262336 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1267. Min Act: -0.0001

Data Index: 899618 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1221. Min Act: -0.0001

Data Index: 481533 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1176. Min Act: -0.0001

Data Index: 298817 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1182. Min Act: -0.0001

Data Index: 611179 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1257. Min Act: -0.0001

Data Index: 511161 (C4 (Web Text))

Max Activating Token Index: 268