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

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

Neuron 2719 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.7433. Min Act: -0.0001

Data Index: 525951 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.7292. Min Act: -0.0001

Data Index: 265329 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.7513. Min Act: -0.0000

Data Index: 806904 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.2449. Min Act: -0.0001

Data Index: 18122 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.4052. Min Act: -0.0000

Data Index: 433357 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.3394. Min Act: -0.0001

Data Index: 10607 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1697. Min Act: -0.0001

Data Index: 271853 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.4441. Min Act: -0.0001

Data Index: 645580 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1210. Min Act: -0.0001

Data Index: 215697 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1194. Min Act: -0.0000

Data Index: 25577 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.3874. Min Act: -0.0000

Data Index: 577375 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1726. Min Act: -0.0001

Data Index: 935445 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1599. Min Act: -0.0001

Data Index: 939694 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 4.7513. Min Range: -4.7513

Max Act: 3.9982. Min Act: -0.0000

Data Index: 888732 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.1541. Min Act: -0.0000

Data Index: 670754 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.0996. Min Act: -0.0001

Data Index: 517616 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 4.7513. Min Range: -4.7513

Max Act: 3.9243. Min Act: -0.0001

Data Index: 106103 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.0849. Min Act: -0.0000

Data Index: 551296 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.2048. Min Act: -0.0001

Data Index: 1313013 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 4.7513. Min Range: -4.7513

Max Act: 4.0416. Min Act: -0.0001

Data Index: 366816 (C4 (Web Text))

Max Activating Token Index: 385