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

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

Neuron 343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1160941 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2943. Min Act: -0.0001

Data Index: 585966 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2888. Min Act: -0.0001

Data Index: 370185 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2651. Min Act: -0.0001

Data Index: 334270 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2705. Min Act: -0.0001

Data Index: 424832 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1111009 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2563. Min Act: -0.0001

Data Index: 873097 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2577. Min Act: -0.0001

Data Index: 792496 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2414. Min Act: -0.0001

Data Index: 710105 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1261707 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2472. Min Act: -0.0001

Data Index: 719702 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2467. Min Act: -0.0001

Data Index: 277320 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1030641 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2423. Min Act: -0.0001

Data Index: 20385 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1245206 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1105390 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1126142 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2539. Min Act: -0.0001

Data Index: 861030 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2474. Min Act: -0.0001

Data Index: 671608 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2386. Min Act: -0.0001

Data Index: 910505 (C4 (Web Text))

Max Activating Token Index: 84