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

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

Neuron 316 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0791. Min Range: -2.0791

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1386479 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 2.0791. Min Range: -2.0791

Max Act: 2.0135. Min Act: -0.0000

Data Index: 1435035 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 2.0791. Min Range: -2.0791

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1650141 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1601623 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7841. Min Act: 0.0000

Data Index: 1525618 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1374412 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1607077 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.9299. Min Act: -0.0000

Data Index: 1462666 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1454834 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1523239 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7832. Min Act: -0.0000

Data Index: 1485047 (Python Code)

Max Activating Token Index: 772

Text #11

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7543. Min Act: 0.0000

Data Index: 1492547 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1529261 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1483419 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1396547 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1410614 (Python Code)

Max Activating Token Index: 540

Text #16

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6348. Min Act: -0.0000

Data Index: 1478004 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6901. Min Act: -0.0000

Data Index: 1474689 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1503120 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 2.0791. Min Range: -2.0791

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1388687 (Python Code)

Max Activating Token Index: 525