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

Dataset: The Pile

Neuron 540 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: 0.3958. Min Range: -0.3958

Max Act: 0.3958. Min Act: -0.0000

Data Index: 838217 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1198206 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3243. Min Act: -0.0000

Data Index: 410297 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3337. Min Act: -0.0000

Data Index: 232253 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3066. Min Act: -0.0000

Data Index: 946010 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3118. Min Act: -0.0000

Data Index: 561967 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1039017 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1177451 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1303651 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1593086 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1431622 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1674050 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1615531 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2989. Min Act: -0.0000

Data Index: 627466 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2959. Min Act: -0.0000

Data Index: 349354 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2872. Min Act: -0.0000

Data Index: 606457 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2788. Min Act: -0.0000

Data Index: 500547 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2855. Min Act: -0.0000

Data Index: 162088 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1283009 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2764. Min Act: -0.0000

Data Index: 775535 (The Pile)

Max Activating Token Index: 635