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

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

Neuron 4437 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3438. Min Range: -1.3438

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.3438. Min Range: -1.3438

Max Act: 1.1672. Min Act: -0.0000

Data Index: 447084 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.3438. Min Range: -1.3438

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1245701 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.3438. Min Range: -1.3438

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1100404 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9025. Min Act: -0.0000

Data Index: 17575 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9275. Min Act: -0.0000

Data Index: 463539 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1009932 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1201571 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9484. Min Act: -0.0000

Data Index: 721838 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8235. Min Act: -0.0000

Data Index: 226584 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.9651. Min Act: -0.0000

Data Index: 706866 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8491. Min Act: -0.0000

Data Index: 129226 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1035773 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8547. Min Act: -0.0000

Data Index: 53638 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8492. Min Act: -0.0000

Data Index: 819918 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8362. Min Act: -0.0000

Data Index: 253858 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1016648 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1079060 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8119. Min Act: -0.0000

Data Index: 608489 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 1.3438. Min Range: -1.3438

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1079055 (C4 (Web Text))

Max Activating Token Index: 452