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

Dataset: The Pile

Neuron 268 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: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1475600 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1200959 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1637878 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1757450 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1408483 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3236. Min Act: -0.0000

Data Index: 722335 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2993. Min Act: -0.0000

Data Index: 44614 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2830. Min Act: -0.0000

Data Index: 546008 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1054349 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3247. Min Act: -0.0000

Data Index: 425226 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3141. Min Act: -0.0000

Data Index: 643724 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2942. Min Act: -0.0000

Data Index: 898347 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2931. Min Act: -0.0000

Data Index: 194111 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2814. Min Act: -0.0000

Data Index: 811244 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3022. Min Act: -0.0000

Data Index: 478305 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1375865 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1646528 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3173. Min Act: -0.0000

Data Index: 972022 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2855. Min Act: -0.0000

Data Index: 198863 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1652210 (The Pile)

Max Activating Token Index: 411