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

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

Neuron 3591 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: 1.6143. Min Range: -1.6143

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1543811 (Python Code)

Max Activating Token Index: 657

Text #1

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1589096 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1522702 (Python Code)

Max Activating Token Index: 649

Text #3

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1507478 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1524628 (Python Code)

Max Activating Token Index: 716

Text #5

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1459717 (Python Code)

Max Activating Token Index: 906

Text #6

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1484327 (Python Code)

Max Activating Token Index: 280

Text #7

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1426076 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1451224 (Python Code)

Max Activating Token Index: 414

Text #9

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1383813 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1635357 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1597181 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1541139 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1497916 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1361152 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1535253 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1451900 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1619022 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1511365 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 1.6143. Min Range: -1.6143

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1595521 (Python Code)

Max Activating Token Index: 806