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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1343890 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1578514 (Python Code)

Max Activating Token Index: 773

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1251012 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0968. Min Act: -0.0001

Data Index: 728754 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0959. Min Act: -0.0001

Data Index: 623428 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0963. Min Act: -0.0001

Data Index: 264329 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1339258 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0952. Min Act: -0.0001

Data Index: 926425 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1443761 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0908. Min Act: -0.0001

Data Index: 429153 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0932. Min Act: -0.0001

Data Index: 422680 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1554497 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0913. Min Act: -0.0001

Data Index: 368381 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0880. Min Act: -0.0001

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0873. Min Act: -0.0001

Data Index: 604947 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0897. Min Act: -0.0001

Data Index: 868842 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0947. Min Act: -0.0001

Data Index: 494217 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1471543 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0893. Min Act: -0.0001

Data Index: 35198 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0880. Min Act: -0.0001

Data Index: 276378 (C4 (Web Text))

Max Activating Token Index: 508