Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1605420 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1366546 (Python Code)

Max Activating Token Index: 569

Text #2

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6864. Min Act: -0.0001

Data Index: 1537012 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6604. Min Act: -0.0000

Data Index: 1513110 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5883. Min Act: -0.0001

Data Index: 1531354 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5371. Min Act: -0.0001

Data Index: 1642618 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1380469 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5486. Min Act: -0.0001

Data Index: 1430545 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1462993 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1525495 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5570. Min Act: -0.0001

Data Index: 1527671 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1515840 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.5083. Min Act: -0.0001

Data Index: 1488380 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4734. Min Act: -0.0001

Data Index: 1593673 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1600651 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4408. Min Act: -0.0001

Data Index: 1479665 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4154. Min Act: -0.0001

Data Index: 1588403 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1507492 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1521980 (Python Code)

Max Activating Token Index: 182

Text #19

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.4232. Min Act: -0.0000

Data Index: 1566535 (Python Code)

Max Activating Token Index: 192