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

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

Neuron 2618 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: 0.6224. Min Range: -0.6224

Max Act: 0.6224. Min Act: -0.0001

Data Index: 484897 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.6139. Min Act: -0.0001

Data Index: 1112255 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.6080. Min Act: -0.0001

Data Index: 587650 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.6097. Min Act: -0.0001

Data Index: 569428 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1261147 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.6088. Min Act: -0.0001

Data Index: 208071 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5965. Min Act: -0.0001

Data Index: 482473 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5978. Min Act: -0.0001

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5889. Min Act: -0.0001

Data Index: 941373 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5983. Min Act: -0.0001

Data Index: 418631 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5929. Min Act: -0.0001

Data Index: 715212 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5871. Min Act: -0.0001

Data Index: 1226367 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5782. Min Act: -0.0001

Data Index: 248999 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5930. Min Act: -0.0001

Data Index: 555698 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1321618 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5814. Min Act: -0.0001

Data Index: 837220 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5900. Min Act: -0.0001

Data Index: 919613 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5773. Min Act: -0.0001

Data Index: 706867 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5827. Min Act: -0.0002

Data Index: 1216105 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1042181 (C4 (Web Text))

Max Activating Token Index: 285