Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1615. Min Range: -1.1615

Max Act: 1.1615. Min Act: -0.0000

Data Index: 78231 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1551644 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1363809 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.1615. Min Range: -1.1615

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1463286 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7456. Min Act: -0.0000

Data Index: 958617 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1265350 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1482905 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1533512 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1469107 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1767527 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7890. Min Act: -0.0000

Data Index: 747940 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1501957 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.5468. Min Act: -0.0000

Data Index: 547836 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7033. Min Act: -0.0000

Data Index: 898891 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.6824. Min Act: -0.0000

Data Index: 62443 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7490. Min Act: -0.0000

Data Index: 848879 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1028245 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7545. Min Act: -0.0000

Data Index: 783381 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1420142 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 1.1615. Min Range: -1.1615

Max Act: 0.7214. Min Act: -0.0000

Data Index: 788078 (The Pile)

Max Activating Token Index: 114