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

Dataset: The Pile

Neuron 906 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: 1.2515. Min Range: -1.2515

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1223687 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1085815 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.0367. Min Act: -0.0000

Data Index: 732841 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1198991 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1385529 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9425. Min Act: -0.0000

Data Index: 435030 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1753966 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8899. Min Act: -0.0000

Data Index: 900010 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1030988 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8800. Min Act: -0.0000

Data Index: 468146 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7183. Min Act: -0.0000

Data Index: 130689 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1269004 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1940548 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1502940 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1089991 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7118. Min Act: -0.0000

Data Index: 8683 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7392. Min Act: -0.0000

Data Index: 867425 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1812664 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.6800. Min Act: -0.0000

Data Index: 197095 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1275078 (The Pile)

Max Activating Token Index: 713