Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5473 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.8444. Min Act: -0.0002

Data Index: 219651 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.8082. Min Act: -0.0002

Data Index: 580791 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7795. Min Act: -0.0002

Data Index: 593280 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7783. Min Act: -0.0003

Data Index: 933663 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7591. Min Act: -0.0002

Data Index: 285306 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7759. Min Act: -0.0002

Data Index: 1248921 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7726. Min Act: -0.0003

Data Index: 1012626 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7491. Min Act: -0.0002

Data Index: 1231961 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7684. Min Act: -0.0002

Data Index: 598839 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7502. Min Act: -0.0002

Data Index: 851852 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7473. Min Act: -0.0002

Data Index: 279846 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7362. Min Act: -0.0002

Data Index: 1006783 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7141. Min Act: -0.0003

Data Index: 220075 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7245. Min Act: -0.0002

Data Index: 836814 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7145. Min Act: -0.0002

Data Index: 649845 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7036. Min Act: -0.0002

Data Index: 430875 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7141. Min Act: -0.0002

Data Index: 196176 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6933. Min Act: -0.0002

Data Index: 300390 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7147. Min Act: -0.0003

Data Index: 8437 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7091. Min Act: -0.0002

Data Index: 882111 (C4 (Web Text))

Max Activating Token Index: 161