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

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

Neuron 2540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9135. Min Range: -4.9135

Max Act: 4.9135. Min Act: -0.0000

Data Index: 1413972 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.9494. Min Act: -0.0000

Data Index: 1371254 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.8470. Min Act: -0.0000

Data Index: 1446651 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 4.9135. Min Range: -4.9135

Max Act: 4.1224. Min Act: -0.0000

Data Index: 1648477 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.9504. Min Act: -0.0000

Data Index: 1460807 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.8557. Min Act: -0.0000

Data Index: 1463825 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.9816. Min Act: -0.0000

Data Index: 1627048 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.6977. Min Act: -0.0000

Data Index: 1606165 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.9876. Min Act: -0.0000

Data Index: 1506127 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.8050. Min Act: -0.0000

Data Index: 1501253 (Python Code)

Max Activating Token Index: 460

Text #10

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.3882. Min Act: -0.0000

Data Index: 1466743 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.3642. Min Act: -0.0000

Data Index: 1500467 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.3461. Min Act: -0.0000

Data Index: 1587874 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.2870. Min Act: -0.0000

Data Index: 1390420 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.4003. Min Act: -0.0000

Data Index: 1623548 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.4934. Min Act: -0.0000

Data Index: 1455024 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.1836. Min Act: -0.0000

Data Index: 1533575 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.3166. Min Act: 0.0001

Data Index: 1527821 (Python Code)

Max Activating Token Index: 454

Text #18

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.4363. Min Act: -0.0000

Data Index: 1533878 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 4.9135. Min Range: -4.9135

Max Act: 3.1296. Min Act: -0.0000

Data Index: 1589463 (Python Code)

Max Activating Token Index: 840