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

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

Neuron 4482 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0000

Data Index: 723158 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1186. Min Act: -0.0000

Data Index: 481318 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1012. Min Act: -0.0000

Data Index: 179137 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1040. Min Act: -0.0000

Data Index: 647890 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0983. Min Act: -0.0000

Data Index: 88910 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1259580 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0990. Min Act: -0.0000

Data Index: 201515 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1011. Min Act: -0.0000

Data Index: 216359 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0972. Min Act: -0.0000

Data Index: 931389 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1214488 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1054521 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0944. Min Act: -0.0000

Data Index: 269025 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0932. Min Act: -0.0000

Data Index: 14487 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0973. Min Act: -0.0000

Data Index: 60673 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0930. Min Act: -0.0000

Data Index: 320531 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0883. Min Act: -0.0000

Data Index: 710276 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0893. Min Act: -0.0000

Data Index: 16253 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0859. Min Act: -0.0000

Data Index: 118453 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0865. Min Act: -0.0000

Data Index: 307471 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1059688 (C4 (Web Text))

Max Activating Token Index: 430