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

Dataset: The Pile

Neuron 1578 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1307. Min Range: -11.1307

Max Act: 11.1307. Min Act: -0.0000

Data Index: 983165 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.8628. Min Act: -0.0000

Data Index: 1417344 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.9733. Min Act: -0.0000

Data Index: 1289228 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.7846. Min Act: -0.0000

Data Index: 593888 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.8753. Min Act: -0.0000

Data Index: 1167019 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.6558. Min Act: -0.0000

Data Index: 108547 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.6476. Min Act: -0.0000

Data Index: 1123899 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.9835. Min Act: -0.0000

Data Index: 230518 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.7469. Min Act: -0.0000

Data Index: 1032632 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.2451. Min Act: -0.0000

Data Index: 440984 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.3639. Min Act: -0.0000

Data Index: 933463 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.4951. Min Act: -0.0000

Data Index: 990737 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.1083. Min Act: -0.0000

Data Index: 797264 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.2257. Min Act: -0.0000

Data Index: 169487 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 11.1307. Min Range: -11.1307

Max Act: 9.9113. Min Act: -0.0000

Data Index: 1021245 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.3320. Min Act: -0.0000

Data Index: 938475 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 11.1307. Min Range: -11.1307

Max Act: 9.7614. Min Act: -0.0000

Data Index: 562274 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.0081. Min Act: -0.0000

Data Index: 1536959 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 11.1307. Min Range: -11.1307

Max Act: 10.1074. Min Act: -0.0000

Data Index: 1897792 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 11.1307. Min Range: -11.1307

Max Act: 9.9303. Min Act: -0.0000

Data Index: 390306 (The Pile)

Max Activating Token Index: 642