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

Dataset: The Pile

Neuron 1669 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: 0.6453. Min Range: -0.6453

Max Act: 0.6453. Min Act: 0.0000

Data Index: 434948 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1745630 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5817. Min Act: -0.0000

Data Index: 959957 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5654. Min Act: 0.0000

Data Index: 1386327 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1143395 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5502. Min Act: 0.0000

Data Index: 1386806 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5263. Min Act: 0.0000

Data Index: 1477285 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1611984 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1405635 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1262547 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1578382 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5124. Min Act: 0.0000

Data Index: 1422217 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5201. Min Act: 0.0000

Data Index: 856841 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1506926 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5263. Min Act: -0.0000

Data Index: 54904 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4965. Min Act: 0.0000

Data Index: 1722457 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1485422 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1092403 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4996. Min Act: 0.0000

Data Index: 1481249 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.4809. Min Act: 0.0000

Data Index: 1489806 (The Pile)

Max Activating Token Index: 519