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

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

Neuron 3203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.7007. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 3.0526. Min Range: -3.0526

Max Act: 3.0526. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.9046. Min Act: -0.0000

Data Index: 386955 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.5554. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.7609. Min Act: -0.0000

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.6449. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.5688. Min Act: -0.0000

Data Index: 343666 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.5971. Min Act: -0.0000

Data Index: 11278 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.5630. Min Act: -0.0000

Data Index: 106363 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4175. Min Act: -0.0000

Data Index: 1138012 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.5011. Min Act: -0.0000

Data Index: 1344399 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4856. Min Act: -0.0000

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.3351. Min Act: -0.0000

Data Index: 1235198 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4546. Min Act: -0.0000

Data Index: 1168410 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1079270 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1050175 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1284479 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1224718 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.3465. Min Act: -0.0000

Data Index: 510725 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 3.0526. Min Range: -3.0526

Max Act: 2.4561. Min Act: -0.0000

Data Index: 589915 (C4 (Web Text))

Max Activating Token Index: 857