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

Dataset: The Pile

Neuron 2977 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: 5.4369. Min Range: -5.4369

Max Act: 5.4369. Min Act: -0.0000

Data Index: 1551034 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.1287. Min Act: -0.0000

Data Index: 245360 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.1453. Min Act: -0.0000

Data Index: 1151044 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.2232. Min Act: -0.0000

Data Index: 360759 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.1707. Min Act: -0.0000

Data Index: 1616413 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.1329. Min Act: -0.0000

Data Index: 1728687 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.2048. Min Act: -0.0000

Data Index: 1544650 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.0535. Min Act: -0.0000

Data Index: 1325475 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.9993. Min Act: -0.0000

Data Index: 1754887 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.7709. Min Act: -0.0000

Data Index: 102531 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.7132. Min Act: -0.0000

Data Index: 554236 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.9011. Min Act: -0.0000

Data Index: 43955 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.9092. Min Act: -0.0000

Data Index: 60322 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.9146. Min Act: -0.0000

Data Index: 959979 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.0168. Min Act: -0.0000

Data Index: 1706518 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.8291. Min Act: -0.0000

Data Index: 64559 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.8734. Min Act: -0.0000

Data Index: 1641913 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.7800. Min Act: -0.0000

Data Index: 147094 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.9780. Min Act: -0.0000

Data Index: 1508234 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 5.4369. Min Range: -5.4369

Max Act: 4.7685. Min Act: -0.0000

Data Index: 1303324 (The Pile)

Max Activating Token Index: 525