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

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

Neuron 942 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.4530. Min Act: -0.0000

Data Index: 615661 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.3390. Min Act: -0.0001

Data Index: 443398 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2717. Min Act: -0.0000

Data Index: 138537 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2460. Min Act: -0.0000

Data Index: 58995 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2422. Min Act: -0.0001

Data Index: 512507 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1385938 (Python Code)

Max Activating Token Index: 877

Text #6

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1305439 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2250. Min Act: -0.0000

Data Index: 523286 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2122. Min Act: -0.0001

Data Index: 188275 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2124. Min Act: -0.0001

Data Index: 36187 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1084371 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1909. Min Act: -0.0000

Data Index: 682433 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.2063. Min Act: -0.0000

Data Index: 395403 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1013026 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1256469 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1837. Min Act: -0.0000

Data Index: 842703 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1363584 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1764. Min Act: -0.0000

Data Index: 640674 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1820. Min Act: -0.0000

Data Index: 62148 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.4530. Min Range: -0.4530

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1472924 (Python Code)

Max Activating Token Index: 870