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

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

Neuron 2692 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: 0.9383. Min Range: -0.9383

Max Act: 0.9383. Min Act: -0.0000

Data Index: 928031 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8992. Min Act: -0.0000

Data Index: 366416 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8851. Min Act: -0.0000

Data Index: 761807 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1335191 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7982. Min Act: -0.0000

Data Index: 507590 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8557. Min Act: -0.0000

Data Index: 561908 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8205. Min Act: -0.0000

Data Index: 966869 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8134. Min Act: -0.0000

Data Index: 133331 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7960. Min Act: -0.0000

Data Index: 784374 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8236. Min Act: -0.0000

Data Index: 957752 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7868. Min Act: -0.0000

Data Index: 966650 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8029. Min Act: -0.0000

Data Index: 671406 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8001. Min Act: -0.0000

Data Index: 821879 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8201. Min Act: -0.0000

Data Index: 649696 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8052. Min Act: -0.0000

Data Index: 431062 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7882. Min Act: -0.0000

Data Index: 179582 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7620. Min Act: -0.0000

Data Index: 712107 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7850. Min Act: -0.0000

Data Index: 422626 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8343. Min Act: -0.0000

Data Index: 348925 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7605. Min Act: -0.0000

Data Index: 915829 (C4 (Web Text))

Max Activating Token Index: 86