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

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

Neuron 161 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7875. Min Act: -0.0002

Data Index: 1029785 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7264. Min Act: -0.0002

Data Index: 1273904 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7159. Min Act: -0.0002

Data Index: 1099814 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6906. Min Act: -0.0003

Data Index: 1000792 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7079. Min Act: -0.0002

Data Index: 1245875 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6937. Min Act: -0.0002

Data Index: 514375 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6805. Min Act: -0.0002

Data Index: 147443 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6835. Min Act: -0.0003

Data Index: 1100603 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6792. Min Act: -0.0002

Data Index: 913983 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6648. Min Act: -0.0002

Data Index: 978114 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6597. Min Act: -0.0002

Data Index: 456976 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6558. Min Act: -0.0002

Data Index: 1316537 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6461. Min Act: -0.0002

Data Index: 26701 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6621. Min Act: -0.0002

Data Index: 124515 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6625. Min Act: -0.0002

Data Index: 1145916 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6401. Min Act: -0.0002

Data Index: 526843 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6326. Min Act: -0.0003

Data Index: 780998 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6394. Min Act: -0.0003

Data Index: 330636 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6370. Min Act: -0.0002

Data Index: 1102220 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6494. Min Act: -0.0002

Data Index: 767613 (C4 (Web Text))

Max Activating Token Index: 160