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

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

Neuron 4785 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: 0.9967. Min Range: -0.9967

Max Act: 0.9265. Min Act: -0.0000

Data Index: 296635 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1293633 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8910. Min Act: -0.0000

Data Index: 747641 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1183991 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8787. Min Act: -0.0000

Data Index: 682818 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1122858 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8882. Min Act: -0.0000

Data Index: 983441 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9067. Min Act: -0.0000

Data Index: 976793 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9565. Min Act: -0.0000

Data Index: 623869 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8959. Min Act: -0.0000

Data Index: 458928 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9003. Min Act: -0.0000

Data Index: 1004622 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8515. Min Act: -0.0000

Data Index: 603054 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8645. Min Act: -0.0000

Data Index: 531880 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8397. Min Act: -0.0000

Data Index: 323485 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8904. Min Act: -0.0000

Data Index: 263675 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7897. Min Act: -0.0000

Data Index: 557485 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8364. Min Act: -0.0000

Data Index: 432551 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8817. Min Act: -0.0000

Data Index: 388679 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8417. Min Act: -0.0000

Data Index: 519954 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8810. Min Act: -0.0000

Data Index: 554724 (C4 (Web Text))

Max Activating Token Index: 710