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

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

Neuron 932 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: 5.7280. Min Range: -5.7280

Max Act: 5.7280. Min Act: -0.0000

Data Index: 208462 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.7339. Min Act: -0.0000

Data Index: 163975 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.7255. Min Act: -0.0000

Data Index: 656092 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.3342. Min Act: -0.0000

Data Index: 4507 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.6460. Min Act: -0.0000

Data Index: 205175 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.5860. Min Act: -0.0000

Data Index: 1191868 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.3788. Min Act: -0.0000

Data Index: 1218082 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.2021. Min Act: 0.0001

Data Index: 1116426 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.1418. Min Act: -0.0000

Data Index: 726439 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.2460. Min Act: 0.0001

Data Index: 911108 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 5.7280. Min Range: -5.7280

Max Act: 4.3994. Min Act: -0.0000

Data Index: 825992 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.8738. Min Act: -0.0000

Data Index: 114230 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.8067. Min Act: -0.0000

Data Index: 182482 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.7573. Min Act: -0.0000

Data Index: 664796 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.7290. Min Act: -0.0000

Data Index: 903947 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.7015. Min Act: -0.0000

Data Index: 1248147 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.6683. Min Act: -0.0000

Data Index: 116063 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.6449. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.6411. Min Act: -0.0000

Data Index: 91612 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 5.7280. Min Range: -5.7280

Max Act: 3.8009. Min Act: -0.0000

Data Index: 1190937 (C4 (Web Text))

Max Activating Token Index: 757