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

Dataset: The Pile

Neuron 1548 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: 1.0550. Min Range: -1.0550

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1389702 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9462. Min Act: -0.0000

Data Index: 57318 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9074. Min Act: -0.0000

Data Index: 828718 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8676. Min Act: -0.0000

Data Index: 212053 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8699. Min Act: -0.0000

Data Index: 604905 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8369. Min Act: -0.0000

Data Index: 621695 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7996. Min Act: -0.0000

Data Index: 556746 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8133. Min Act: -0.0000

Data Index: 741182 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1923841 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1612661 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7829. Min Act: -0.0000

Data Index: 483592 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7679. Min Act: -0.0000

Data Index: 654692 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8481. Min Act: -0.0000

Data Index: 745520 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7757. Min Act: -0.0000

Data Index: 595905 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1961378 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7284. Min Act: -0.0000

Data Index: 363026 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1007449 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.6904. Min Act: -0.0000

Data Index: 861440 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.6519. Min Act: -0.0000

Data Index: 502133 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1087632 (The Pile)

Max Activating Token Index: 212