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

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

Neuron 59 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1503053 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1626152 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5453. Min Act: -0.0001

Data Index: 1477814 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5929. Min Act: -0.0001

Data Index: 1632009 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5433. Min Act: -0.0001

Data Index: 1474355 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5098. Min Act: -0.0001

Data Index: 1490851 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5224. Min Act: -0.0001

Data Index: 1564757 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1371996 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1520772 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4720. Min Act: -0.0001

Data Index: 1628905 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1404077 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1536354 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1564487 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1599457 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1619672 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1408072 (Python Code)

Max Activating Token Index: 509

Text #16

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1369027 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4327. Min Act: -0.0001

Data Index: 1438914 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1656516 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1423294 (Python Code)

Max Activating Token Index: 862