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

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

Neuron 672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1012159 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1551816 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1324593 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1072. Min Act: -0.0002

Data Index: 265537 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1161. Min Act: -0.0002

Data Index: 631213 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1073. Min Act: -0.0002

Data Index: 381407 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1062. Min Act: -0.0002

Data Index: 863109 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1107. Min Act: -0.0002

Data Index: 118381 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1335448 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1032. Min Act: -0.0002

Data Index: 713009 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1033. Min Act: -0.0002

Data Index: 91321 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1064089 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0978. Min Act: -0.0002

Data Index: 897593 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0930. Min Act: -0.0002

Data Index: 825836 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1029. Min Act: -0.0002

Data Index: 818856 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1315716 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1301403 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0819. Min Act: -0.0002

Data Index: 333682 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0966. Min Act: -0.0002

Data Index: 216855 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1029. Min Act: -0.0002

Data Index: 225983 (C4 (Web Text))

Max Activating Token Index: 12