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

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

Neuron 5902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0779. Min Act: -0.0000

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1350312 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0512. Min Act: -0.0000

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.1477. Min Act: -0.0000

Data Index: 655032 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.1136. Min Act: -0.0000

Data Index: 698901 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.1147. Min Act: -0.0000

Data Index: 459439 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1535944 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0052. Min Act: -0.0000

Data Index: 955461 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.1534. Min Range: -1.1534

Max Act: 1.0362. Min Act: -0.0000

Data Index: 256913 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.9338. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.9358. Min Act: -0.0000

Data Index: 990688 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1220034 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1235192 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.8983. Min Act: -0.0000

Data Index: 407838 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.8716. Min Act: -0.0000

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.8176. Min Act: -0.0000

Data Index: 28397 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.8924. Min Act: -0.0000

Data Index: 898695 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.1534. Min Range: -1.1534

Max Act: 0.7736. Min Act: -0.0000

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 930