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

Dataset: The Pile

Neuron 2309 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2877. Min Range: -3.2877

Max Act: 3.1498. Min Act: -0.0000

Data Index: 1059363 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 3.2877. Min Range: -3.2877

Max Act: 3.2877. Min Act: -0.0000

Data Index: 1146974 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.9062. Min Act: -0.0000

Data Index: 44766 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.5950. Min Act: -0.0000

Data Index: 781499 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.5856. Min Act: -0.0000

Data Index: 577053 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.9471. Min Act: -0.0000

Data Index: 929217 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.7884. Min Act: -0.0000

Data Index: 1799128 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.1177. Min Act: -0.0000

Data Index: 1371333 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.1527. Min Act: -0.0000

Data Index: 529750 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.4502. Min Act: -0.0000

Data Index: 1117845 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.2469. Min Act: -0.0000

Data Index: 469079 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.2165. Min Act: -0.0000

Data Index: 385868 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.3211. Min Act: -0.0000

Data Index: 1761786 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.3029. Min Act: -0.0000

Data Index: 1539464 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 3.2877. Min Range: -3.2877

Max Act: 1.9584. Min Act: -0.0000

Data Index: 1726126 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.2981. Min Act: -0.0000

Data Index: 874034 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.0643. Min Act: -0.0000

Data Index: 1756132 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 3.2877. Min Range: -3.2877

Max Act: 1.9466. Min Act: -0.0000

Data Index: 352803 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.0305. Min Act: -0.0000

Data Index: 934124 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 3.2877. Min Range: -3.2877

Max Act: 2.1338. Min Act: -0.0000

Data Index: 1264398 (The Pile)

Max Activating Token Index: 520