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

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

Neuron 1102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6856. Min Act: -0.0001

Data Index: 828688 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5916. Min Act: -0.0000

Data Index: 185715 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1225918 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1155376 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5631. Min Act: -0.0000

Data Index: 570876 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1116826 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5646. Min Act: -0.0001

Data Index: 356637 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1095946 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5547. Min Act: -0.0000

Data Index: 771444 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1109158 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5279. Min Act: -0.0000

Data Index: 118654 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5283. Min Act: -0.0000

Data Index: 600402 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5371. Min Act: -0.0000

Data Index: 903113 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5170. Min Act: -0.0000

Data Index: 7289 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4999. Min Act: -0.0000

Data Index: 673074 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5135. Min Act: -0.0000

Data Index: 976210 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5068. Min Act: -0.0001

Data Index: 1042423 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5019. Min Act: -0.0000

Data Index: 22767 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4813. Min Act: -0.0001

Data Index: 598762 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4944. Min Act: -0.0000

Data Index: 457666 (C4 (Web Text))

Max Activating Token Index: 749