Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.3652. Min Act: -0.0000

Data Index: 855924 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1177140 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1812999 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1943. Min Act: -0.0000

Data Index: 39950 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1444. Min Act: -0.0000

Data Index: 314259 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0993. Min Act: -0.0000

Data Index: 963961 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1773154 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1315345 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1631753 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1944352 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0640. Min Act: -0.0000

Data Index: 72900 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 1.3652. Min Range: -1.3652

Max Act: 0.9298. Min Act: -0.0000

Data Index: 5093 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1732438 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1759244 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.3652. Min Range: -1.3652

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1340514 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.0004. Min Act: -0.0000

Data Index: 121602 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 1.3652. Min Range: -1.3652

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1031036 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 1.3652. Min Range: -1.3652

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1018440 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.3652. Min Range: -1.3652

Max Act: 0.9879. Min Act: -0.0000

Data Index: 648779 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 1.3652. Min Range: -1.3652

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1794974 (The Pile)

Max Activating Token Index: 293