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

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

Neuron 1166 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: 2.4538. Min Range: -2.4538

Max Act: 2.3462. Min Act: -0.0000

Data Index: 1402805 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.4538. Min Act: -0.0000

Data Index: 1580784 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9839. Min Act: 0.0000

Data Index: 1423182 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1407184 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1645533 (Python Code)

Max Activating Token Index: 642

Text #5

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9916. Min Act: 0.0000

Data Index: 1481599 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9665. Min Act: 0.0001

Data Index: 1582419 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.0261. Min Act: -0.0000

Data Index: 1599032 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9236. Min Act: 0.0000

Data Index: 1419679 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.9046. Min Act: -0.0000

Data Index: 1416867 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.7109. Min Act: -0.0000

Data Index: 1601370 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.6916. Min Act: 0.0000

Data Index: 1510396 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.7498. Min Act: -0.0000

Data Index: 1483579 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.7384. Min Act: 0.0001

Data Index: 1609130 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.7276. Min Act: 0.0001

Data Index: 1556822 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.6202. Min Act: 0.0001

Data Index: 1494582 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.6725. Min Act: 0.0001

Data Index: 1610354 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.7229. Min Act: 0.0001

Data Index: 1364980 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.6207. Min Act: 0.0001

Data Index: 1367115 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 2.4538. Min Range: -2.4538

Max Act: 1.6902. Min Act: 0.0000

Data Index: 1606689 (Python Code)

Max Activating Token Index: 1022