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

Dataset: The Pile

Neuron 1782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1295271 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1681849 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1348812 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1273156 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6119. Min Act: -0.0000

Data Index: 48984 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1625877 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6984. Min Act: -0.0000

Data Index: 574987 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.7312. Min Act: -0.0000

Data Index: 344698 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1715886 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6415. Min Act: -0.0000

Data Index: 692544 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1370839 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1264277 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1399682 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1484432 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1289672 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1377282 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1114483 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1904354 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5454. Min Act: -0.0000

Data Index: 604179 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 0.8123. Min Range: -0.8123

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1090782 (The Pile)

Max Activating Token Index: 54