Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6429. Min Act: -0.0001

Data Index: 60504 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1067260 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6415. Min Act: -0.0001

Data Index: 1330133 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5172. Min Act: -0.0001

Data Index: 1318915 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4629. Min Act: -0.0001

Data Index: 1191867 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5038. Min Act: -0.0001

Data Index: 820697 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4818. Min Act: -0.0001

Data Index: 204441 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4631. Min Act: -0.0001

Data Index: 797854 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4894. Min Act: -0.0001

Data Index: 852710 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4812. Min Act: -0.0001

Data Index: 307721 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4431. Min Act: -0.0001

Data Index: 1274906 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5020. Min Act: -0.0001

Data Index: 648998 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4170. Min Act: -0.0001

Data Index: 128956 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4488. Min Act: -0.0001

Data Index: 694018 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1285615 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4003. Min Act: -0.0001

Data Index: 916564 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4008. Min Act: -0.0001

Data Index: 833855 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4315. Min Act: -0.0001

Data Index: 517204 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4373. Min Act: -0.0001

Data Index: 985688 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4179. Min Act: -0.0001

Data Index: 1159628 (C4 (Web Text))

Max Activating Token Index: 159