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

Dataset: The Pile

Neuron 1140 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0707. Min Range: -1.0707

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1961042 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 1.0707. Min Range: -1.0707

Max Act: 1.0446. Min Act: -0.0000

Data Index: 902276 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 1.0707. Min Range: -1.0707

Max Act: 1.0377. Min Act: -0.0000

Data Index: 442035 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8985. Min Act: -0.0000

Data Index: 881404 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1727100 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1382216 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1962577 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1777505 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1222600 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1852283 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1773099 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8056. Min Act: -0.0000

Data Index: 373427 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8386. Min Act: -0.0000

Data Index: 205940 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1537591 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1620644 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1040836 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8000. Min Act: -0.0000

Data Index: 498943 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1380830 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8021. Min Act: -0.0000

Data Index: 642541 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1675682 (The Pile)

Max Activating Token Index: 15