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

Dataset: The Pile

Neuron 2959 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6157. Min Range: -10.6157

Max Act: 10.6157. Min Act: -0.0000

Data Index: 1451709 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 10.6157. Min Range: -10.6157

Max Act: 10.2342. Min Act: -0.0000

Data Index: 679831 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 10.6157. Min Range: -10.6157

Max Act: 10.0807. Min Act: -0.0000

Data Index: 778188 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 10.6157. Min Range: -10.6157

Max Act: 10.0039. Min Act: -0.0000

Data Index: 1573526 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.7583. Min Act: -0.0000

Data Index: 1420794 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.8386. Min Act: -0.0000

Data Index: 528181 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.5136. Min Act: -0.0000

Data Index: 234187 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.7952. Min Act: -0.0000

Data Index: 1306530 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.8832. Min Act: -0.0000

Data Index: 1340999 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.4423. Min Act: -0.0000

Data Index: 388062 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.6631. Min Act: -0.0000

Data Index: 1028237 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.2113. Min Act: -0.0000

Data Index: 1457828 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.6819. Min Act: -0.0000

Data Index: 1506669 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.0815. Min Act: -0.0000

Data Index: 1619868 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.5015. Min Act: -0.0000

Data Index: 1194960 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.3829. Min Act: -0.0000

Data Index: 416394 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.4990. Min Act: -0.0000

Data Index: 894334 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.6083. Min Act: -0.0000

Data Index: 1360458 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 10.6157. Min Range: -10.6157

Max Act: 8.9545. Min Act: -0.0000

Data Index: 669939 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 10.6157. Min Range: -10.6157

Max Act: 9.5062. Min Act: -0.0000

Data Index: 357403 (The Pile)

Max Activating Token Index: 580