Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3882 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1575418 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1534763 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1319358 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1644655 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4803. Min Act: -0.0000

Data Index: 455885 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4635. Min Act: -0.0000

Data Index: 668341 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1561664 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4389. Min Act: -0.0001

Data Index: 282358 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1369705 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1139246 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4609. Min Act: -0.0001

Data Index: 732621 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4144. Min Act: -0.0000

Data Index: 449111 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1409195 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4010. Min Act: -0.0001

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4271. Min Act: -0.0000

Data Index: 259159 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4236. Min Act: -0.0001

Data Index: 866994 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1023643 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4027. Min Act: -0.0001

Data Index: 515479 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4133. Min Act: -0.0001

Data Index: 862398 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.5776. Min Range: -0.5776

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1474530 (Python Code)

Max Activating Token Index: 82