Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.6749. Min Act: -0.0001

Data Index: 1432183 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.1513. Min Act: -0.0001

Data Index: 1629593 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0947. Min Act: -0.0001

Data Index: 1562416 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0724. Min Act: -0.0001

Data Index: 1636929 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.8826. Min Act: -0.0001

Data Index: 1471472 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.8638. Min Act: -0.0001

Data Index: 1522443 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0238. Min Act: -0.0001

Data Index: 1513921 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.9193. Min Act: -0.0001

Data Index: 1531382 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0461. Min Act: -0.0001

Data Index: 1581045 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0382. Min Act: -0.0001

Data Index: 1526789 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 3.6749. Min Range: -3.6749

Max Act: 3.0057. Min Act: -0.0001

Data Index: 1418251 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.8513. Min Act: -0.0001

Data Index: 1520536 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.8255. Min Act: -0.0001

Data Index: 1502657 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.7843. Min Act: -0.0001

Data Index: 1517736 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.7629. Min Act: -0.0001

Data Index: 1459333 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.8806. Min Act: -0.0001

Data Index: 1618598 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.4513. Min Act: -0.0001

Data Index: 1493087 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.6455. Min Act: -0.0001

Data Index: 1397863 (Python Code)

Max Activating Token Index: 445

Text #18

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.4716. Min Act: -0.0001

Data Index: 1636267 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 3.6749. Min Range: -3.6749

Max Act: 2.5912. Min Act: -0.0001

Data Index: 1540377 (Python Code)

Max Activating Token Index: 1018