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

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

Neuron 852 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: 2.7570. Min Range: -2.7570

Max Act: 2.7570. Min Act: -0.0000

Data Index: 813686 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.6353. Min Act: -0.0000

Data Index: 383328 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.5277. Min Act: -0.0000

Data Index: 67361 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1028188 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1434005 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.1612. Min Act: -0.0000

Data Index: 425463 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.0066. Min Act: -0.0000

Data Index: 977634 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.1890. Min Act: 0.0000

Data Index: 556013 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.1986. Min Act: -0.0000

Data Index: 1448205 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 2.7570. Min Range: -2.7570

Max Act: 2.1079. Min Act: -0.0000

Data Index: 1416604 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1392678 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.9774. Min Act: -0.0000

Data Index: 245844 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.9375. Min Act: -0.0000

Data Index: 1432142 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.7304. Min Act: -0.0000

Data Index: 719606 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1591508 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1186954 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.8454. Min Act: -0.0000

Data Index: 1479543 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1593023 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1624184 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 2.7570. Min Range: -2.7570

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1462257 (Python Code)

Max Activating Token Index: 820