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

Dataset: The Pile

Neuron 3632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1151. Min Range: -3.1151

Max Act: 3.1151. Min Act: -0.0000

Data Index: 1183911 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.2019. Min Act: -0.0000

Data Index: 307456 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.4667. Min Act: -0.0000

Data Index: 504138 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.1683. Min Act: -0.0000

Data Index: 102995 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.0080. Min Act: -0.0000

Data Index: 900070 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.2177. Min Act: -0.0000

Data Index: 1396973 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1496200 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.8072. Min Act: -0.0000

Data Index: 319484 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.0040. Min Act: -0.0000

Data Index: 189232 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1545342 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.9026. Min Act: -0.0000

Data Index: 791704 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.7071. Min Act: -0.0000

Data Index: 1282618 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1316826 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.7547. Min Act: -0.0000

Data Index: 996230 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.7252. Min Act: -0.0000

Data Index: 1097225 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1439526 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.2033. Min Act: -0.0000

Data Index: 224149 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1468837 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.1872. Min Act: -0.0000

Data Index: 446242 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 3.1151. Min Range: -3.1151

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1712592 (The Pile)

Max Activating Token Index: 14