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

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

Neuron 2118 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3545. Min Act: -0.0000

Data Index: 843731 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2651. Min Act: -0.0000

Data Index: 849524 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2640. Min Act: -0.0000

Data Index: 109825 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2298. Min Act: -0.0000

Data Index: 342193 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1099371 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1340. Min Act: -0.0000

Data Index: 575713 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1692. Min Act: -0.0000

Data Index: 889241 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1695. Min Act: -0.0000

Data Index: 567998 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1228. Min Act: -0.0000

Data Index: 835039 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1476. Min Act: -0.0000

Data Index: 58226 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1501. Min Act: -0.0000

Data Index: 364280 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1479. Min Act: -0.0000

Data Index: 290859 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1400. Min Act: -0.0000

Data Index: 972853 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1360. Min Act: -0.0000

Data Index: 203851 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1334467 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1525. Min Act: -0.0000

Data Index: 383989 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1053552 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1060207 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1041. Min Act: -0.0000

Data Index: 616306 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1049795 (C4 (Web Text))

Max Activating Token Index: 765