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

Dataset: The Pile

Neuron 4925 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: 0.1300. Min Range: -0.1300

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1814166 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1116257 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1884509 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1986680 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1191. Min Act: -0.0000

Data Index: 380804 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1030115 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1165. Min Act: -0.0000

Data Index: 99219 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1772885 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1101. Min Act: -0.0000

Data Index: 345523 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1054. Min Act: -0.0000

Data Index: 461611 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1017. Min Act: -0.0000

Data Index: 432110 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1448080 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1003. Min Act: -0.0000

Data Index: 327706 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1278889 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1876254 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1559756 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1743818 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1002. Min Act: -0.0000

Data Index: 206935 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0976. Min Act: -0.0000

Data Index: 67999 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0957. Min Act: -0.0000

Data Index: 27533 (The Pile)

Max Activating Token Index: 439