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

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

Neuron 760 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: 1.5543. Min Range: -1.5543

Max Act: 1.5543. Min Act: -0.0002

Data Index: 598410 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.5495. Min Act: -0.0002

Data Index: 35332 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.5239. Min Act: -0.0002

Data Index: 1307521 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.5421. Min Act: -0.0002

Data Index: 396082 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.5147. Min Act: -0.0002

Data Index: 917559 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.5040. Min Act: -0.0002

Data Index: 501592 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4644. Min Act: -0.0002

Data Index: 324718 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4775. Min Act: -0.0002

Data Index: 672799 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4728. Min Act: -0.0002

Data Index: 38794 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4330. Min Act: -0.0002

Data Index: 913631 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4330. Min Act: -0.0002

Data Index: 372735 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4289. Min Act: -0.0003

Data Index: 102986 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4403. Min Act: -0.0002

Data Index: 153102 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4374. Min Act: -0.0003

Data Index: 846752 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4357. Min Act: -0.0002

Data Index: 102380 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4137. Min Act: -0.0002

Data Index: 457414 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.3862. Min Act: -0.0003

Data Index: 928323 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4026. Min Act: -0.0002

Data Index: 289835 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.4034. Min Act: -0.0002

Data Index: 349873 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.3795. Min Act: -0.0002

Data Index: 767191 (C4 (Web Text))

Max Activating Token Index: 153