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

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

Neuron 3760 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7753. Min Range: -4.7753

Max Act: 4.7753. Min Act: -0.0000

Data Index: 995430 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 4.7753. Min Range: -4.7753

Max Act: 4.2508. Min Act: -0.0000

Data Index: 737550 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 4.7753. Min Range: -4.7753

Max Act: 4.0106. Min Act: -0.0000

Data Index: 696894 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.6250. Min Act: -0.0000

Data Index: 404762 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.8890. Min Act: -0.0000

Data Index: 1049972 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.1124. Min Act: 0.0000

Data Index: 1322850 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.9557. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.6065. Min Act: -0.0000

Data Index: 330766 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.7928. Min Act: -0.0000

Data Index: 1056494 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.6185. Min Act: -0.0000

Data Index: 91560 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.7041. Min Act: -0.0000

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.5093. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.6274. Min Act: -0.0000

Data Index: 1200157 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.1576. Min Act: -0.0000

Data Index: 940918 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.4184. Min Act: 0.0000

Data Index: 758918 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 4.7753. Min Range: -4.7753

Max Act: 2.6280. Min Act: -0.0000

Data Index: 1285359 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.1689. Min Act: -0.0000

Data Index: 860366 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.3083. Min Act: -0.0000

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 4.7753. Min Range: -4.7753

Max Act: 3.1235. Min Act: -0.0000

Data Index: 74536 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 4.7753. Min Range: -4.7753

Max Act: 2.8461. Min Act: -0.0000

Data Index: 133225 (C4 (Web Text))

Max Activating Token Index: 21