Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3249 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8712. Min Act: -0.0001

Data Index: 1017196 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.9175. Min Act: -0.0001

Data Index: 463595 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8711. Min Act: -0.0001

Data Index: 895001 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7682. Min Act: -0.0001

Data Index: 324925 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7990. Min Act: -0.0001

Data Index: 20999 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8101. Min Act: -0.0001

Data Index: 762628 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8421. Min Act: -0.0001

Data Index: 374847 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.8090. Min Act: -0.0001

Data Index: 700710 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7723. Min Act: -0.0001

Data Index: 186996 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.6772. Min Act: -0.0001

Data Index: 295500 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1056240 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1281565 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7525. Min Act: -0.0001

Data Index: 1134794 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7238. Min Act: -0.0001

Data Index: 1329366 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.7475. Min Act: -0.0001

Data Index: 526562 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.6995. Min Act: -0.0001

Data Index: 118914 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.6953. Min Act: -0.0001

Data Index: 477645 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.6965. Min Act: -0.0001

Data Index: 975432 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.9175. Min Range: -0.9175

Max Act: 0.6466. Min Act: -0.0001

Data Index: 910989 (C4 (Web Text))

Max Activating Token Index: 778