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

Dataset: The Pile

Neuron 932 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: 0.7144. Min Range: -0.7144

Max Act: 0.7144. Min Act: -0.0000

Data Index: 135898 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1456867 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1003511 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1375873 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4777. Min Act: -0.0000

Data Index: 978464 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4930. Min Act: -0.0000

Data Index: 664913 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4908. Min Act: -0.0000

Data Index: 598323 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5069. Min Act: -0.0000

Data Index: 442093 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5029. Min Act: -0.0000

Data Index: 436993 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1167140 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5088. Min Act: -0.0000

Data Index: 514064 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4577. Min Act: -0.0000

Data Index: 680423 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.5243. Min Act: -0.0000

Data Index: 536003 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4230. Min Act: -0.0000

Data Index: 627295 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1757545 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4632. Min Act: 0.0000

Data Index: 1232474 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1657684 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1783867 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1737920 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.7144. Min Range: -0.7144

Max Act: 0.4232. Min Act: -0.0000

Data Index: 577344 (The Pile)

Max Activating Token Index: 378