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

Dataset: The Pile

Neuron 4902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0514. Min Range: -1.0514

Max Act: 1.0514. Min Act: -0.0000

Data Index: 317606 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9663. Min Act: -0.0001

Data Index: 331038 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8791. Min Act: -0.0000

Data Index: 704256 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8760. Min Act: -0.0000

Data Index: 569890 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7764. Min Act: -0.0000

Data Index: 997380 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8547. Min Act: -0.0000

Data Index: 199356 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8457. Min Act: -0.0000

Data Index: 438488 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1280749 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1700872 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7613. Min Act: -0.0000

Data Index: 513059 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7631. Min Act: -0.0000

Data Index: 181339 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7724. Min Act: -0.0000

Data Index: 250484 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7466. Min Act: -0.0000

Data Index: 782623 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1062081 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1417665 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7540. Min Act: -0.0000

Data Index: 773745 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7799. Min Act: -0.0000

Data Index: 221524 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7428. Min Act: -0.0000

Data Index: 308172 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1170114 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1635096 (The Pile)

Max Activating Token Index: 954