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

Dataset: The Pile

Neuron 1958 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8867. Min Act: -0.0000

Data Index: 25099 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5780. Min Act: -0.0000

Data Index: 449142 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5798. Min Act: -0.0000

Data Index: 666520 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1601298 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1707986 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1683655 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1724086 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1378263 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4897. Min Act: -0.0000

Data Index: 446799 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1162517 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1531549 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1988639 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1027870 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4336. Min Act: -0.0000

Data Index: 723293 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4320. Min Act: -0.0000

Data Index: 5634 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1932156 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1752925 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4099. Min Act: -0.0000

Data Index: 245459 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4179. Min Act: -0.0000

Data Index: 557433 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1457763 (The Pile)

Max Activating Token Index: 617