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

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

Neuron 2919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1557215 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1464878 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1528119 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1515609 (Python Code)

Max Activating Token Index: 838

Text #4

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1578262 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1550081 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.0353. Min Act: -0.0000

Data Index: 145807 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1553624 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1585374 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1425302 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 1.5298. Min Range: -1.5298

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1390097 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1357242 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1565796 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1536730 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1641971 (Python Code)

Max Activating Token Index: 532

Text #15

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1648066 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1429512 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1560355 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1398762 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.5298. Min Range: -1.5298

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1591301 (Python Code)

Max Activating Token Index: 130