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

Dataset: The Pile

Neuron 707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.5345. Min Act: -0.0000

Data Index: 351229 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1053529 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4868. Min Act: -0.0000

Data Index: 350741 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1397107 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4743. Min Act: -0.0000

Data Index: 292144 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1317847 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4280. Min Act: -0.0000

Data Index: 978226 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4146. Min Act: -0.0000

Data Index: 843511 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4132. Min Act: -0.0000

Data Index: 575800 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4257. Min Act: -0.0000

Data Index: 807341 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4120. Min Act: -0.0000

Data Index: 987101 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4124. Min Act: -0.0000

Data Index: 159012 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4077. Min Act: -0.0000

Data Index: 593047 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1706264 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1794834 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4139. Min Act: -0.0000

Data Index: 831678 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1476828 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3808. Min Act: -0.0000

Data Index: 413171 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3968. Min Act: -0.0000

Data Index: 775852 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4131. Min Act: -0.0000

Data Index: 742091 (The Pile)

Max Activating Token Index: 678