Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1027 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2941. Min Act: -0.0001

Data Index: 354231 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2081. Min Act: -0.0001

Data Index: 121869 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1964. Min Act: -0.0002

Data Index: 489665 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1872. Min Act: -0.0002

Data Index: 892929 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1162. Min Act: -0.0001

Data Index: 508570 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1061745 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1049. Min Act: -0.0002

Data Index: 32507 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0521. Min Act: -0.0001

Data Index: 67984 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1964. Min Act: -0.0002

Data Index: 245315 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0403. Min Act: -0.0001

Data Index: 978822 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0267. Min Act: -0.0001

Data Index: 659 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0314. Min Act: -0.0002

Data Index: 1060465 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0795. Min Act: -0.0002

Data Index: 236551 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0447. Min Act: -0.0002

Data Index: 964902 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0475. Min Act: -0.0002

Data Index: 850663 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0736. Min Act: -0.0001

Data Index: 841014 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1328759 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0350. Min Act: -0.0001

Data Index: 406371 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.9979. Min Act: -0.0002

Data Index: 945992 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0832. Min Act: -0.0001

Data Index: 222768 (C4 (Web Text))

Max Activating Token Index: 31