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

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

Neuron 757 in Layer 0

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: 0.6945. Min Range: -0.6945

Max Act: 0.6945. Min Act: -0.0001

Data Index: 331593 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6658. Min Act: -0.0001

Data Index: 469391 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1327140 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6535. Min Act: -0.0001

Data Index: 378325 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6556. Min Act: -0.0001

Data Index: 26480 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6528. Min Act: -0.0001

Data Index: 85950 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6375. Min Act: -0.0001

Data Index: 614538 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6404. Min Act: -0.0002

Data Index: 722330 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6327. Min Act: -0.0001

Data Index: 230335 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6352. Min Act: -0.0001

Data Index: 289703 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6266. Min Act: -0.0001

Data Index: 323463 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1255210 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6355. Min Act: -0.0001

Data Index: 543896 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6357. Min Act: -0.0001

Data Index: 408721 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1298458 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6226. Min Act: -0.0001

Data Index: 911397 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6175. Min Act: -0.0001

Data Index: 1225532 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6126. Min Act: -0.0001

Data Index: 699880 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1071189 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6108. Min Act: -0.0001

Data Index: 105244 (C4 (Web Text))

Max Activating Token Index: 222