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

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

Neuron 2542 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: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 91067 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0532. Min Act: -0.0002

Data Index: 585326 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1057969 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1235031 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1487643 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0544. Min Act: -0.0002

Data Index: 143674 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1120078 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0485. Min Act: -0.0002

Data Index: 586228 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1638161 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0458. Min Act: -0.0002

Data Index: 586486 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0470. Min Act: -0.0002

Data Index: 854915 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1315976 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0432. Min Act: -0.0002

Data Index: 985763 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1286390 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1445586 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1113918 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1656480 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0435. Min Act: -0.0002

Data Index: 586252 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0427. Min Act: -0.0002

Data Index: 372145 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0432. Min Act: -0.0002

Data Index: 691812 (C4 (Web Text))

Max Activating Token Index: 428