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

Dataset: The Pile

Neuron 2330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1235288 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.2314. Min Act: -0.0000

Data Index: 386245 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9642. Min Act: -0.0000

Data Index: 76273 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0746. Min Act: -0.0000

Data Index: 540990 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0498. Min Act: -0.0000

Data Index: 918438 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0199. Min Act: -0.0000

Data Index: 588482 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1705125 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1790291 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1736521 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9115. Min Act: -0.0000

Data Index: 10384 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8871. Min Act: -0.0000

Data Index: 9797 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9028. Min Act: -0.0000

Data Index: 480590 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1099481 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8463. Min Act: -0.0000

Data Index: 558001 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1038575 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8820. Min Act: -0.0000

Data Index: 756344 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9041. Min Act: -0.0000

Data Index: 732222 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8239. Min Act: -0.0000

Data Index: 19942 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1752189 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8838. Min Act: -0.0000

Data Index: 726688 (The Pile)

Max Activating Token Index: 254