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

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

Neuron 506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2302. Min Act: -0.0000

Data Index: 525894 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0669. Min Act: -0.0000

Data Index: 547007 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0647. Min Act: -0.0000

Data Index: 743387 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1178441 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1145694 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0561. Min Act: -0.0000

Data Index: 73699 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0473. Min Act: -0.0000

Data Index: 989307 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1168676 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0470. Min Act: -0.0000

Data Index: 329671 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1253225 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0454. Min Act: -0.0000

Data Index: 68124 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0405. Min Act: -0.0000

Data Index: 813745 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0421. Min Act: -0.0000

Data Index: 894266 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0483. Min Act: -0.0000

Data Index: 275888 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0446. Min Act: -0.0000

Data Index: 759925 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0397. Min Act: -0.0000

Data Index: 883644 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0424. Min Act: -0.0000

Data Index: 308469 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0432. Min Act: -0.0000

Data Index: 716470 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1284103 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.0424. Min Act: -0.0000

Data Index: 589489 (C4 (Web Text))

Max Activating Token Index: 456