Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3747 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0682. Min Range: -1.0682

Max Act: 1.0682. Min Act: -0.0001

Data Index: 895301 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1364740 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9069. Min Act: -0.0000

Data Index: 748898 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8503. Min Act: -0.0001

Data Index: 47705 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1608054 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1606835 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8059. Min Act: -0.0001

Data Index: 1511998 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8238. Min Act: -0.0000

Data Index: 778438 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8177. Min Act: -0.0000

Data Index: 626669 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8013. Min Act: -0.0000

Data Index: 618918 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1359749 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7825. Min Act: -0.0000

Data Index: 993653 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7570. Min Act: -0.0000

Data Index: 821479 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7276. Min Act: -0.0000

Data Index: 358255 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1233801 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7986. Min Act: -0.0000

Data Index: 301021 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7583. Min Act: -0.0000

Data Index: 579831 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7849. Min Act: -0.0000

Data Index: 833979 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7367. Min Act: -0.0001

Data Index: 866833 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7886. Min Act: -0.0000

Data Index: 656782 (C4 (Web Text))

Max Activating Token Index: 262