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

Dataset: The Pile

Neuron 2865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.6206. Min Act: -0.0000

Data Index: 477468 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1081561 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.4815. Min Act: -0.0000

Data Index: 419206 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1584754 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1704726 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1440. Min Act: -0.0000

Data Index: 167167 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1711883 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1077247 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1614263 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0503. Min Act: -0.0000

Data Index: 349830 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1139544 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1008. Min Act: -0.0000

Data Index: 135417 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0907. Min Act: -0.0000

Data Index: 774316 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1169061 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1276037 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1235786 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1942149 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1390004 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1921560 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 1.6206. Min Range: -1.6206

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1846163 (The Pile)

Max Activating Token Index: 791