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

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

Neuron 6124 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4467. Min Range: -2.4467

Max Act: 2.4467. Min Act: -0.0001

Data Index: 1369862 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 2.4467. Min Range: -2.4467

Max Act: 2.2013. Min Act: -0.0000

Data Index: 1563125 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 2.4467. Min Range: -2.4467

Max Act: 2.0644. Min Act: -0.0000

Data Index: 1445617 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.9526. Min Act: -0.0000

Data Index: 1647567 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.9582. Min Act: -0.0000

Data Index: 1588799 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.9528. Min Act: -0.0000

Data Index: 1640437 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7158. Min Act: -0.0001

Data Index: 1593118 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6720. Min Act: -0.0000

Data Index: 1447179 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1641987 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7275. Min Act: -0.0001

Data Index: 1533649 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1508070 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7269. Min Act: -0.0001

Data Index: 1463148 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1494374 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1619940 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6823. Min Act: -0.0001

Data Index: 1524886 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6920. Min Act: -0.0001

Data Index: 1586477 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1429046 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1591634 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1425547 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.7315. Min Act: -0.0000

Data Index: 1450924 (Python Code)

Max Activating Token Index: 120