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

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

Neuron 1576 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.1394. Min Act: -0.0001

Data Index: 652354 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0694. Min Act: -0.0001

Data Index: 1646035 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1563994 (Python Code)

Max Activating Token Index: 252

Text #3

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0477. Min Act: -0.0001

Data Index: 1565657 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0700. Min Act: -0.0001

Data Index: 1503110 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0908. Min Act: -0.0001

Data Index: 1403275 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0176. Min Act: -0.0001

Data Index: 1647438 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0328. Min Act: -0.0001

Data Index: 1391105 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0028. Min Act: -0.0001

Data Index: 1436152 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1578565 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0015. Min Act: -0.0001

Data Index: 236184 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9401. Min Act: -0.0001

Data Index: 1519518 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1396121 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8885. Min Act: -0.0001

Data Index: 1435345 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9138. Min Act: -0.0001

Data Index: 1019257 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9040. Min Act: -0.0001

Data Index: 1601759 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1394442 (Python Code)

Max Activating Token Index: 1013

Text #17

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9288. Min Act: -0.0001

Data Index: 1502921 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1566650 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1645287 (Python Code)

Max Activating Token Index: 106