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

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

Neuron 4054 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7569. Min Act: 0.0000

Data Index: 1376313 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1124919 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1096184 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7220. Min Act: -0.0000

Data Index: 757456 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7118. Min Act: 0.0000

Data Index: 1378840 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7013. Min Act: -0.0000

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6613. Min Act: -0.0000

Data Index: 633858 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6491. Min Act: -0.0000

Data Index: 663546 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1446493 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1460639 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1527238 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1562657 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1489986 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5465. Min Act: -0.0000

Data Index: 630261 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1149386 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5208. Min Act: -0.0000

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5341. Min Act: -0.0000

Data Index: 946964 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5000. Min Act: -0.0000

Data Index: 609593 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5136. Min Act: -0.0000

Data Index: 883600 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5283. Min Act: -0.0000

Data Index: 180980 (C4 (Web Text))

Max Activating Token Index: 150