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

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

Neuron 1147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.2589. Min Act: -0.0000

Data Index: 828108 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.2363. Min Act: -0.0000

Data Index: 465870 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.1448. Min Act: -0.0000

Data Index: 5845 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.1300. Min Act: -0.0000

Data Index: 1240583 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.0887. Min Act: -0.0000

Data Index: 16799 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.9566. Min Act: -0.0000

Data Index: 647387 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.0350. Min Act: -0.0000

Data Index: 14594 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1468860 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 2.2589. Min Range: -2.2589

Max Act: 2.0101. Min Act: -0.0000

Data Index: 620630 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.8774. Min Act: -0.0000

Data Index: 477810 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.9569. Min Act: -0.0000

Data Index: 193564 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.9363. Min Act: -0.0000

Data Index: 505977 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.7746. Min Act: -0.0000

Data Index: 1227576 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.9131. Min Act: -0.0000

Data Index: 1640659 (Python Code)

Max Activating Token Index: 1016

Text #14

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.8859. Min Act: -0.0000

Data Index: 32438 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.7654. Min Act: -0.0000

Data Index: 340636 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1631261 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.8365. Min Act: -0.0000

Data Index: 718595 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.8318. Min Act: -0.0000

Data Index: 1138646 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 2.2589. Min Range: -2.2589

Max Act: 1.9176. Min Act: -0.0000

Data Index: 211895 (C4 (Web Text))

Max Activating Token Index: 715