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

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

Neuron 268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0002

Data Index: 1630047 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5048. Min Act: -0.0002

Data Index: 133257 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5038. Min Act: -0.0002

Data Index: 1613942 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5044. Min Act: -0.0002

Data Index: 238518 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4898. Min Act: -0.0002

Data Index: 1404914 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4862. Min Act: -0.0002

Data Index: 1371408 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4780. Min Act: -0.0002

Data Index: 1410562 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4724. Min Act: -0.0002

Data Index: 1649968 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4666. Min Act: -0.0002

Data Index: 935370 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4712. Min Act: -0.0002

Data Index: 1569253 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4650. Min Act: -0.0002

Data Index: 627298 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4647. Min Act: -0.0002

Data Index: 1483121 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4517. Min Act: -0.0002

Data Index: 1447801 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4451. Min Act: -0.0002

Data Index: 1526189 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4565. Min Act: -0.0002

Data Index: 1391324 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4441. Min Act: -0.0002

Data Index: 1604195 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4437. Min Act: -0.0002

Data Index: 1627961 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4537. Min Act: -0.0002

Data Index: 1627089 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4424. Min Act: -0.0002

Data Index: 1283227 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4492. Min Act: -0.0002

Data Index: 1523303 (Python Code)

Max Activating Token Index: 798