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

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

Neuron 3855 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.9520. Min Act: -0.0000

Data Index: 326763 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6753. Min Act: 0.0001

Data Index: 1001469 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5959. Min Act: -0.0000

Data Index: 979543 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5823. Min Act: 0.0000

Data Index: 47923 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6075. Min Act: -0.0000

Data Index: 889730 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5751. Min Act: 0.0001

Data Index: 462156 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5522. Min Act: 0.0000

Data Index: 33034 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5503. Min Act: -0.0000

Data Index: 89982 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5627. Min Act: -0.0000

Data Index: 403030 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5461. Min Act: -0.0000

Data Index: 331501 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5209. Min Act: 0.0001

Data Index: 519311 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5099. Min Act: 0.0001

Data Index: 1311163 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5114. Min Act: 0.0000

Data Index: 838542 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1080035 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1193330 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.4969. Min Act: 0.0003

Data Index: 515614 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.5106. Min Act: -0.0000

Data Index: 594998 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.4848. Min Act: -0.0000

Data Index: 145796 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1206790 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.4848. Min Act: 0.0000

Data Index: 364096 (C4 (Web Text))

Max Activating Token Index: 565