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

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

Neuron 587 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: 1.5500. Min Range: -1.5500

Max Act: 1.5500. Min Act: -0.0001

Data Index: 1049889 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1623273 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.4500. Min Act: -0.0001

Data Index: 182439 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.4347. Min Act: -0.0000

Data Index: 25394 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.3440. Min Act: -0.0000

Data Index: 971837 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.2833. Min Act: -0.0001

Data Index: 1112650 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.2144. Min Act: -0.0000

Data Index: 1290911 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.2653. Min Act: -0.0000

Data Index: 990057 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.2998. Min Act: -0.0000

Data Index: 781859 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.2824. Min Act: -0.0001

Data Index: 810272 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1044156 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1526834 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1088. Min Act: -0.0000

Data Index: 15410 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1464868 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1607. Min Act: -0.0001

Data Index: 987901 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1283. Min Act: -0.0001

Data Index: 158839 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1257183 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.1448. Min Act: -0.0000

Data Index: 199929 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.0708. Min Act: -0.0001

Data Index: 396761 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.5500. Min Range: -1.5500

Max Act: 1.0591. Min Act: -0.0000

Data Index: 924308 (C4 (Web Text))

Max Activating Token Index: 88