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

Dataset: The Pile

Neuron 4523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0717. Min Range: -1.0717

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1131190 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9658. Min Act: -0.0000

Data Index: 841166 (The Pile)

Max Activating Token Index: 836

Text #2

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1785090 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9437. Min Act: -0.0000

Data Index: 137709 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1860004 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1819543 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1977127 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1602462 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1287833 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8735. Min Act: -0.0000

Data Index: 824866 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1668691 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.9208. Min Act: -0.0000

Data Index: 379249 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1390624 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1451202 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1900252 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8060. Min Act: -0.0000

Data Index: 307375 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1569635 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8399. Min Act: -0.0000

Data Index: 213548 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1940942 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8070. Min Act: -0.0000

Data Index: 667142 (The Pile)

Max Activating Token Index: 156