Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.3026. Min Act: -0.0001

Data Index: 1258961 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2828. Min Act: -0.0001

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2928. Min Act: -0.0001

Data Index: 556662 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1022788 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1158742 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2600. Min Act: -0.0000

Data Index: 741848 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2500. Min Act: -0.0001

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2563. Min Act: -0.0001

Data Index: 398611 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1303404 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1142082 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2507. Min Act: -0.0001

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2584. Min Act: -0.0001

Data Index: 279859 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2281. Min Act: -0.0001

Data Index: 391921 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1342927 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2668. Min Act: -0.0001

Data Index: 905349 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2294. Min Act: -0.0001

Data Index: 187728 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2318. Min Act: -0.0001

Data Index: 322403 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1015550 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2363. Min Act: -0.0001

Data Index: 850190 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2265. Min Act: -0.0001

Data Index: 97974 (C4 (Web Text))

Max Activating Token Index: 1017