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

Dataset: The Pile

Neuron 900 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: 1.8826. Min Range: -1.8826

Max Act: 1.8826. Min Act: -0.0000

Data Index: 858496 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.8225. Min Act: -0.0000

Data Index: 994858 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.5550. Min Act: -0.0000

Data Index: 975602 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1815787 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1281801 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1668615 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.4098. Min Act: -0.0000

Data Index: 712370 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.8826. Min Range: -1.8826

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1867431 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1796078 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1108832 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1420138 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.8147. Min Act: -0.0000

Data Index: 207773 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0307. Min Act: -0.0000

Data Index: 575372 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2370. Min Act: -0.0000

Data Index: 938306 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0250. Min Act: -0.0000

Data Index: 611974 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1046798 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0792. Min Act: -0.0000

Data Index: 12682 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1578492 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.8826. Min Range: -1.8826

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1176084 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.8826. Min Range: -1.8826

Max Act: 0.9038. Min Act: -0.0000

Data Index: 427908 (The Pile)

Max Activating Token Index: 456