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

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

Neuron 1485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.4858. Min Act: -0.0000

Data Index: 871354 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1104179 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1127226 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1756. Min Act: -0.0000

Data Index: 495276 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.2143. Min Act: -0.0000

Data Index: 307825 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1650. Min Act: -0.0000

Data Index: 33964 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1634. Min Act: -0.0000

Data Index: 857351 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1096. Min Act: -0.0000

Data Index: 870614 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1028. Min Act: -0.0000

Data Index: 417707 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1977. Min Act: -0.0000

Data Index: 288831 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0968. Min Act: -0.0000

Data Index: 466145 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0736. Min Act: -0.0000

Data Index: 155909 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1256793 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1145120 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1563246 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 1.4858. Min Range: -1.4858

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1097192 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1012801 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0037. Min Act: -0.0000

Data Index: 115977 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.1891. Min Act: -0.0000

Data Index: 70680 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 1.4858. Min Range: -1.4858

Max Act: 1.0526. Min Act: -0.0000

Data Index: 94149 (C4 (Web Text))

Max Activating Token Index: 789