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

Dataset: The Pile

Neuron 4678 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: 0.0000

Data Index: 196304 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1011412 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1223956 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0633. Min Act: -0.0000

Data Index: 862286 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0602. Min Act: -0.0000

Data Index: 231626 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0596. Min Act: 0.0000

Data Index: 352235 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0587. Min Act: -0.0000

Data Index: 268515 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0581. Min Act: 0.0000

Data Index: 785729 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0566. Min Act: -0.0000

Data Index: 776948 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0562. Min Act: -0.0000

Data Index: 446691 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0559. Min Act: 0.0000

Data Index: 279158 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0551. Min Act: 0.0000

Data Index: 858227 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1035458 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0540. Min Act: 0.0000

Data Index: 1404138 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0538. Min Act: 0.0000

Data Index: 629453 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1826151 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1484057 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1005620 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1309698 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0510. Min Act: 0.0000

Data Index: 1335479 (The Pile)

Max Activating Token Index: 65