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

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

Neuron 4482 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: 0.7422. Min Range: -0.7422

Max Act: 0.7199. Min Act: -0.0001

Data Index: 1468539 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1400211 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1361613 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1553786 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1439359 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7146. Min Act: -0.0001

Data Index: 1637447 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7387. Min Act: -0.0001

Data Index: 1631285 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7181. Min Act: -0.0001

Data Index: 1515977 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6808. Min Act: -0.0001

Data Index: 1316984 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1621606 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6501. Min Act: -0.0001

Data Index: 1630854 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6499. Min Act: -0.0001

Data Index: 1477752 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5862. Min Act: -0.0001

Data Index: 1606136 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5867. Min Act: -0.0001

Data Index: 1458022 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5486. Min Act: -0.0001

Data Index: 1389546 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5205. Min Act: -0.0001

Data Index: 1427628 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5210. Min Act: -0.0001

Data Index: 1580945 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1015057 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5273. Min Act: -0.0001

Data Index: 900544 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4554. Min Act: -0.0001

Data Index: 59196 (C4 (Web Text))

Max Activating Token Index: 767