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

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

Neuron 1082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1655436 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.1154. Min Act: -0.0000

Data Index: 1509260 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0641. Min Act: -0.0000

Data Index: 1416236 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1621172 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1426628 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1655995 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1413942 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.6097. Min Act: -0.0001

Data Index: 1651759 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1473982 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1583407 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4949. Min Act: -0.0000

Data Index: 512758 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1390209 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1373504 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1592284 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1485120 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4795. Min Act: -0.0000

Data Index: 794814 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1326070 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3473. Min Act: -0.0000

Data Index: 1548271 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1557097 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3630. Min Act: -0.0000

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 425