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

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

Neuron 320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4984. Min Act: -0.0000

Data Index: 123977 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3974. Min Act: -0.0000

Data Index: 736982 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3530. Min Act: -0.0000

Data Index: 300788 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1359249 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3068. Min Act: -0.0000

Data Index: 636130 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2881. Min Act: -0.0000

Data Index: 291117 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2453. Min Act: -0.0000

Data Index: 237772 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2521. Min Act: -0.0000

Data Index: 617242 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2444. Min Act: -0.0000

Data Index: 427831 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1029940 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2295. Min Act: -0.0000

Data Index: 117668 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2426. Min Act: -0.0000

Data Index: 720190 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.2155. Min Act: -0.0000

Data Index: 501288 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1375912 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1481606 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1501685 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1917. Min Act: -0.0000

Data Index: 530541 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1426712 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1921. Min Act: -0.0000

Data Index: 198674 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.1764. Min Act: -0.0000

Data Index: 990274 (C4 (Web Text))

Max Activating Token Index: 689