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

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

Neuron 3770 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: 1.5599. Min Range: -1.5599

Max Act: 1.4488. Min Act: -0.0001

Data Index: 1558275 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1476412 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.5599. Min Act: -0.0001

Data Index: 1512444 (Python Code)

Max Activating Token Index: 600

Text #3

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.4048. Min Act: -0.0001

Data Index: 1540680 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1650567 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.3302. Min Act: -0.0001

Data Index: 1648038 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.3072. Min Act: -0.0001

Data Index: 1487976 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1547410 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1382846 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2348. Min Act: -0.0001

Data Index: 1637339 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.1205. Min Act: -0.0001

Data Index: 1656154 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2324. Min Act: -0.0001

Data Index: 1457684 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2219. Min Act: -0.0001

Data Index: 1577298 (Python Code)

Max Activating Token Index: 434

Text #13

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2035. Min Act: -0.0001

Data Index: 1364510 (Python Code)

Max Activating Token Index: 257

Text #14

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1495911 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.1526. Min Act: -0.0001

Data Index: 1462130 (Python Code)

Max Activating Token Index: 969

Text #16

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.1143. Min Act: -0.0001

Data Index: 1486622 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.1596. Min Act: -0.0001

Data Index: 1644210 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.1931. Min Act: -0.0001

Data Index: 1408899 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 1.5599. Min Range: -1.5599

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1603536 (Python Code)

Max Activating Token Index: 946