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

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

Neuron 274 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8625. Min Act: -0.0002

Data Index: 1416923 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8784. Min Act: -0.0002

Data Index: 1408111 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8172. Min Act: -0.0002

Data Index: 1219677 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8265. Min Act: -0.0002

Data Index: 1386128 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8063. Min Act: -0.0002

Data Index: 1457937 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8070. Min Act: -0.0002

Data Index: 421591 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8305. Min Act: -0.0002

Data Index: 1572810 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7805. Min Act: -0.0002

Data Index: 1169316 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7942. Min Act: -0.0002

Data Index: 542099 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7504. Min Act: -0.0002

Data Index: 1604661 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7981. Min Act: -0.0002

Data Index: 1555951 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7901. Min Act: -0.0002

Data Index: 605885 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6415. Min Act: -0.0002

Data Index: 1409890 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8288. Min Act: -0.0002

Data Index: 1415446 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7921. Min Act: -0.0002

Data Index: 626887 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7230. Min Act: -0.0002

Data Index: 748704 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7840. Min Act: -0.0002

Data Index: 410101 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7668. Min Act: -0.0002

Data Index: 877696 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7591. Min Act: -0.0002

Data Index: 1631039 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7472. Min Act: -0.0002

Data Index: 1428685 (Python Code)

Max Activating Token Index: 429