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

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

Neuron 4651 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: 0.1119. Min Range: -0.1119

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1114793 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1032. Min Act: -0.0002

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0956. Min Act: -0.0002

Data Index: 368782 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0920. Min Act: -0.0002

Data Index: 260626 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1361634 (Python Code)

Max Activating Token Index: 228

Text #5

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0779. Min Act: -0.0002

Data Index: 552627 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0774. Min Act: -0.0002

Data Index: 555257 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0725. Min Act: -0.0002

Data Index: 49446 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1634075 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0734. Min Act: -0.0002

Data Index: 553615 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0715. Min Act: -0.0002

Data Index: 433656 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1500262 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1257791 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1487581 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1384057 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1585119 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1416518 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0690. Min Act: -0.0002

Data Index: 396819 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0691. Min Act: -0.0002

Data Index: 677037 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0673. Min Act: -0.0002

Data Index: 395647 (C4 (Web Text))

Max Activating Token Index: 995