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

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

Neuron 2070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.7339. Min Act: -0.0000

Data Index: 62986 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.8064. Min Act: -0.0000

Data Index: 550568 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.8921. Min Act: -0.0000

Data Index: 974501 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.6786. Min Act: -0.0000

Data Index: 683388 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.6298. Min Act: -0.0000

Data Index: 702597 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.5824. Min Act: -0.0000

Data Index: 419774 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.6194. Min Act: -0.0000

Data Index: 286137 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1087390 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4010. Min Act: -0.0000

Data Index: 547467 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4838. Min Act: -0.0000

Data Index: 861354 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4394. Min Act: -0.0000

Data Index: 543549 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1031265 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.3399. Min Act: -0.0000

Data Index: 406380 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4500. Min Act: -0.0000

Data Index: 787587 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4360. Min Act: -0.0000

Data Index: 451136 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1297460 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.3104. Min Act: -0.0000

Data Index: 900471 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4291. Min Act: -0.0000

Data Index: 290096 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1236581 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.8921. Min Range: -1.8921

Max Act: 1.4987. Min Act: -0.0000

Data Index: 1162365 (C4 (Web Text))

Max Activating Token Index: 852