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

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

Neuron 3942 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: 4.6191. Min Range: -4.6191

Max Act: 4.6191. Min Act: -0.0002

Data Index: 303971 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 4.6191. Min Range: -4.6191

Max Act: 4.2249. Min Act: -0.0002

Data Index: 1213615 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.9278. Min Act: -0.0002

Data Index: 137337 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.9116. Min Act: -0.0002

Data Index: 786318 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.9040. Min Act: -0.0002

Data Index: 903476 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7828. Min Act: -0.0002

Data Index: 1046201 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7890. Min Act: -0.0002

Data Index: 379714 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.8756. Min Act: -0.0002

Data Index: 713642 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7758. Min Act: -0.0002

Data Index: 402395 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7762. Min Act: -0.0002

Data Index: 613123 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7241. Min Act: -0.0002

Data Index: 1098428 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7336. Min Act: -0.0002

Data Index: 1271710 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6888. Min Act: -0.0003

Data Index: 167650 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6876. Min Act: -0.0003

Data Index: 1167807 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6837. Min Act: -0.0003

Data Index: 425971 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7860. Min Act: -0.0002

Data Index: 556585 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6717. Min Act: -0.0002

Data Index: 1282851 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6574. Min Act: -0.0002

Data Index: 764286 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.6365. Min Act: -0.0002

Data Index: 254778 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 4.6191. Min Range: -4.6191

Max Act: 3.7084. Min Act: -0.0002

Data Index: 1066350 (C4 (Web Text))

Max Activating Token Index: 19