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

Dataset: The Pile

Neuron 3628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1356807 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5737. Min Act: -0.0000

Data Index: 270983 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1811476 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5231. Min Act: -0.0000

Data Index: 61057 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.4267. Min Act: -0.0000

Data Index: 168779 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.4294. Min Act: -0.0000

Data Index: 781061 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3542. Min Act: -0.0000

Data Index: 171621 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1372689 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1825014 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1874004 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1511. Min Act: -0.0000

Data Index: 898815 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1595171 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2622. Min Act: -0.0000

Data Index: 488673 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1677. Min Act: -0.0000

Data Index: 632395 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1504. Min Act: -0.0000

Data Index: 919166 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1298. Min Act: -0.0000

Data Index: 444714 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1797276 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.5921. Min Range: -1.5921

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1317471 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1459381 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0038. Min Act: -0.0000

Data Index: 511793 (The Pile)

Max Activating Token Index: 1021