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

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

Neuron 657 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: 0.7206. Min Range: -0.7206

Max Act: 0.7206. Min Act: -0.0002

Data Index: 646959 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6217. Min Act: -0.0002

Data Index: 1306237 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6221. Min Act: -0.0002

Data Index: 746232 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6296. Min Act: -0.0002

Data Index: 1186677 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6121. Min Act: -0.0002

Data Index: 1024305 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6075. Min Act: -0.0002

Data Index: 808330 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5939. Min Act: -0.0002

Data Index: 761403 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5885. Min Act: -0.0002

Data Index: 755340 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5924. Min Act: -0.0002

Data Index: 687837 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5961. Min Act: -0.0002

Data Index: 1262392 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5967. Min Act: -0.0002

Data Index: 669626 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5972. Min Act: -0.0002

Data Index: 771605 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5794. Min Act: -0.0002

Data Index: 910545 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5929. Min Act: -0.0002

Data Index: 294920 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5723. Min Act: -0.0002

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5849. Min Act: -0.0002

Data Index: 775073 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5802. Min Act: -0.0002

Data Index: 304683 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5712. Min Act: -0.0002

Data Index: 1181895 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5709. Min Act: -0.0002

Data Index: 1058714 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5751. Min Act: -0.0002

Data Index: 298353 (C4 (Web Text))

Max Activating Token Index: 249