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

Dataset: The Pile

Neuron 4724 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: 0.7200. Min Range: -0.7200

Max Act: 0.5714. Min Act: -0.0000

Data Index: 408956 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1446933 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1470661 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6631. Min Act: -0.0000

Data Index: 278657 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1277941 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1147473 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1674692 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5929. Min Act: -0.0000

Data Index: 369920 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5130. Min Act: -0.0000

Data Index: 30401 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1692293 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5341. Min Act: -0.0000

Data Index: 836208 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5340. Min Act: -0.0000

Data Index: 740645 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1799611 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1205961 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4972. Min Act: -0.0000

Data Index: 707500 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1243505 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5360. Min Act: -0.0000

Data Index: 884214 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1181654 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1153211 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1225525 (The Pile)

Max Activating Token Index: 49