Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1464. Min Act: -0.0001

Data Index: 854719 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1299. Min Act: -0.0001

Data Index: 745955 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1381476 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1066. Min Act: -0.0001

Data Index: 818621 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0996. Min Act: -0.0001

Data Index: 934676 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1519944 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0991. Min Act: -0.0001

Data Index: 551271 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1601400 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1622171 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1480593 (Python Code)

Max Activating Token Index: 764

Text #10

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1200416 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1622880 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1362528 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1381742 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1653032 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1393734 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1536476 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1396452 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0761. Min Act: -0.0001

Data Index: 386150 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1562542 (Python Code)

Max Activating Token Index: 926