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

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

Neuron 3701 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2995. Min Range: -1.2995

Max Act: 1.2995. Min Act: -0.0000

Data Index: 99650 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1290239 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.5442. Min Act: -0.0000

Data Index: 949043 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1656795 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.5111. Min Act: -0.0000

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4933. Min Act: -0.0000

Data Index: 148500 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4995. Min Act: -0.0000

Data Index: 570390 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.5095. Min Act: -0.0000

Data Index: 386000 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1443731 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1522893 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1505116 (Python Code)

Max Activating Token Index: 883

Text #12

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1577383 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1410509 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1518542 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1581484 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4791. Min Act: -0.0000

Data Index: 147558 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4426. Min Act: -0.0000

Data Index: 325561 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.2995. Min Range: -1.2995

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1528988 (Python Code)

Max Activating Token Index: 50