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

Dataset: The Pile

Neuron 2774 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: 1.1491. Min Range: -1.1491

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1059190 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 1.1491. Min Range: -1.1491

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1831718 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 1.1491. Min Range: -1.1491

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1615436 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1427661 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.9368. Min Act: -0.0000

Data Index: 334728 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8524. Min Act: -0.0000

Data Index: 904516 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8291. Min Act: -0.0000

Data Index: 893893 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1632028 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8442. Min Act: -0.0000

Data Index: 479174 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7318. Min Act: -0.0000

Data Index: 823086 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8786. Min Act: -0.0000

Data Index: 356462 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8986. Min Act: -0.0000

Data Index: 230888 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1588775 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8565. Min Act: -0.0000

Data Index: 931551 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1114851 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1089182 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8194. Min Act: -0.0000

Data Index: 832023 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1264238 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8168. Min Act: -0.0000

Data Index: 585283 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1561716 (The Pile)

Max Activating Token Index: 253