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

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

Neuron 5332 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0000

Data Index: 152740 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0471. Min Act: -0.0000

Data Index: 534393 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1440861 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1319950 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1310321 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0440. Min Act: 0.0000

Data Index: 912490 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0451. Min Act: -0.0000

Data Index: 970734 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1461475 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1006115 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1105708 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1015994 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0407. Min Act: 0.0000

Data Index: 1270315 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1195058 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0419. Min Act: -0.0000

Data Index: 393772 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1270157 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0396. Min Act: -0.0000

Data Index: 61496 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0396. Min Act: 0.0000

Data Index: 1631261 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0000

Data Index: 897140 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0403. Min Act: -0.0000

Data Index: 826945 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0416. Min Act: -0.0000

Data Index: 794382 (C4 (Web Text))

Max Activating Token Index: 276