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

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

Neuron 1722 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: 1.4653. Min Range: -1.4653

Max Act: 1.4653. Min Act: -0.0002

Data Index: 818541 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.3359. Min Act: -0.0002

Data Index: 921466 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.3165. Min Act: -0.0002

Data Index: 412539 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.3142. Min Act: -0.0002

Data Index: 1070342 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2942. Min Act: -0.0002

Data Index: 674375 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2977. Min Act: -0.0002

Data Index: 635967 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2980. Min Act: -0.0002

Data Index: 489543 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2860. Min Act: -0.0002

Data Index: 897320 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2839. Min Act: -0.0002

Data Index: 176232 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2653. Min Act: -0.0002

Data Index: 450801 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2690. Min Act: -0.0002

Data Index: 1030549 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2604. Min Act: -0.0002

Data Index: 995108 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2791. Min Act: -0.0002

Data Index: 299624 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2771. Min Act: -0.0002

Data Index: 565194 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2747. Min Act: -0.0002

Data Index: 583562 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2688. Min Act: -0.0002

Data Index: 23262 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2774. Min Act: -0.0002

Data Index: 7070 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2603. Min Act: -0.0002

Data Index: 549601 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2504. Min Act: -0.0002

Data Index: 973796 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.4653. Min Range: -1.4653

Max Act: 1.2434. Min Act: -0.0002

Data Index: 513346 (C4 (Web Text))

Max Activating Token Index: 177