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

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

Neuron 2029 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: 1.4815. Min Range: -1.4815

Max Act: 1.4815. Min Act: -0.0002

Data Index: 666945 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3480. Min Act: -0.0002

Data Index: 928020 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3925. Min Act: -0.0002

Data Index: 1418749 (Python Code)

Max Activating Token Index: 644

Text #3

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3434. Min Act: -0.0002

Data Index: 1517272 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3182. Min Act: -0.0002

Data Index: 628882 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2579. Min Act: -0.0002

Data Index: 216024 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2616. Min Act: -0.0002

Data Index: 1604189 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2766. Min Act: -0.0002

Data Index: 1533572 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2492. Min Act: -0.0002

Data Index: 1574103 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2462. Min Act: -0.0002

Data Index: 214280 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2791. Min Act: -0.0002

Data Index: 1569059 (Python Code)

Max Activating Token Index: 761

Text #11

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2518. Min Act: -0.0002

Data Index: 1434672 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2809. Min Act: -0.0002

Data Index: 1329689 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2047. Min Act: -0.0002

Data Index: 714230 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2314. Min Act: -0.0002

Data Index: 1639644 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2214. Min Act: -0.0002

Data Index: 1566109 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1972. Min Act: -0.0002

Data Index: 1012920 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1763. Min Act: -0.0002

Data Index: 1393230 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1465. Min Act: -0.0002

Data Index: 1487781 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1952. Min Act: -0.0002

Data Index: 818454 (C4 (Web Text))

Max Activating Token Index: 9