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

Dataset: The Pile

Neuron 4202 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: 0.5331. Min Range: -0.5331

Max Act: 0.5331. Min Act: -0.0000

Data Index: 862118 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4559. Min Act: -0.0000

Data Index: 852660 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1364801 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4946. Min Act: -0.0000

Data Index: 746129 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1572582 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4576. Min Act: -0.0000

Data Index: 167767 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4787. Min Act: -0.0000

Data Index: 836939 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4678. Min Act: -0.0000

Data Index: 204032 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1939013 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4407. Min Act: -0.0000

Data Index: 930590 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1022442 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4410. Min Act: -0.0000

Data Index: 378136 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4777. Min Act: -0.0000

Data Index: 131305 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1862828 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3944. Min Act: -0.0000

Data Index: 770074 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4305. Min Act: -0.0000

Data Index: 172713 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4177. Min Act: -0.0000

Data Index: 808372 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1432206 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1420536 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3578. Min Act: -0.0000

Data Index: 226739 (The Pile)

Max Activating Token Index: 1017