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

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

Neuron 956 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.6079. Min Act: 0.0000

Data Index: 779052 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.3620. Min Act: -0.0000

Data Index: 996796 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1481471 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1343110 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.3723. Min Act: 0.0000

Data Index: 1239516 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1957. Min Act: -0.0000

Data Index: 1197056 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1407157 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.2008. Min Act: 0.0000

Data Index: 213205 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1534376 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1601. Min Act: -0.0000

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0724. Min Act: 0.0000

Data Index: 511646 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0436. Min Act: -0.0000

Data Index: 424917 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0164. Min Act: -0.0000

Data Index: 328177 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1332370 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0733. Min Act: -0.0000

Data Index: 538095 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1413. Min Act: -0.0000

Data Index: 829872 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1438443 (Python Code)

Max Activating Token Index: 531

Text #17

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9360. Min Act: -0.0000

Data Index: 277837 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0459. Min Act: -0.0000

Data Index: 777444 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9715. Min Act: -0.0000

Data Index: 147881 (C4 (Web Text))

Max Activating Token Index: 308