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

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

Neuron 5271 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1643201 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1492405 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1364619 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1433963 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1377003 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1486256 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1481465 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1490310 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1452418 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1404655 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1580765 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 1.7395. Min Range: -1.7395

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1613353 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1360268 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1070141 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1164004 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1655508 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1494803 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1378883 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1439695 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 1.7395. Min Range: -1.7395

Max Act: 0.8502. Min Act: -0.0000

Data Index: 406565 (C4 (Web Text))

Max Activating Token Index: 962