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

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

Neuron 5866 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7935. Min Range: -2.7935

Max Act: 2.7935. Min Act: -0.0000

Data Index: 1397754 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 2.7935. Min Range: -2.7935

Max Act: 2.6362. Min Act: -0.0000

Data Index: 1540793 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 2.7935. Min Range: -2.7935

Max Act: 2.4327. Min Act: -0.0000

Data Index: 1542941 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 2.7935. Min Range: -2.7935

Max Act: 2.2248. Min Act: -0.0000

Data Index: 1498213 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 2.7935. Min Range: -2.7935

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1526051 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.9799. Min Act: -0.0000

Data Index: 1405421 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1515840 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1488380 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.8091. Min Act: -0.0000

Data Index: 1502978 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.7599. Min Act: -0.0000

Data Index: 1396902 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1612994 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.6738. Min Act: -0.0000

Data Index: 1517945 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.7412. Min Act: -0.0000

Data Index: 1385278 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1525080 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1584314 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1430545 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1451611 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.5750. Min Act: -0.0000

Data Index: 1464083 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1586805 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 2.7935. Min Range: -2.7935

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1625187 (Python Code)

Max Activating Token Index: 881