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

Dataset: The Pile

Neuron 5098 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.3854. Min Act: -0.0000

Data Index: 360257 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0756. Min Act: -0.0000

Data Index: 149434 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0988. Min Act: -0.0000

Data Index: 595774 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1360282 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0963. Min Act: -0.0000

Data Index: 268550 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1782. Min Act: -0.0000

Data Index: 847259 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1415689 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0438. Min Act: -0.0000

Data Index: 132781 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1994376 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0099. Min Act: -0.0000

Data Index: 627010 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1059427 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1523. Min Act: -0.0000

Data Index: 539425 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9265. Min Act: -0.0000

Data Index: 721586 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1846796 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9739. Min Act: -0.0000

Data Index: 782156 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9868. Min Act: -0.0000

Data Index: 369678 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1242010 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9063. Min Act: -0.0000

Data Index: 524292 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1168684 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9135. Min Act: -0.0000

Data Index: 88543 (The Pile)

Max Activating Token Index: 284