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

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

Neuron 904 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.7327. Min Act: -0.0000

Data Index: 628937 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1103541 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5798. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1415708 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1033143 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1451208 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1361138 (Python Code)

Max Activating Token Index: 799

Text #9

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1555566 (Python Code)

Max Activating Token Index: 421

Text #10

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4862. Min Act: -0.0000

Data Index: 621339 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4966. Min Act: -0.0000

Data Index: 405242 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4480. Min Act: 0.0000

Data Index: 1414266 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4786. Min Act: -0.0000

Data Index: 813767 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4517. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1240458 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4309. Min Act: -0.0000

Data Index: 191658 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1420460 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4183. Min Act: 0.0001

Data Index: 1530551 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4250. Min Act: -0.0000

Data Index: 156561 (C4 (Web Text))

Max Activating Token Index: 552