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

Dataset: The Pile

Neuron 3231 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: 1.3827. Min Range: -1.3827

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1888331 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1795203 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.1968. Min Act: -0.0000

Data Index: 333088 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.2059. Min Act: -0.0000

Data Index: 277882 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1799957 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1744172 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1370731 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1957012 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.1144. Min Act: -0.0000

Data Index: 562817 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9796. Min Act: -0.0000

Data Index: 741962 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0548. Min Act: -0.0000

Data Index: 423733 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0198. Min Act: -0.0000

Data Index: 616088 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0819. Min Act: -0.0000

Data Index: 318252 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1917116 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1448648 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1288991 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1738807 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1766527 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1108050 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1802261 (The Pile)

Max Activating Token Index: 872