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

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

Neuron 516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.8229. Min Act: -0.0000

Data Index: 1598920 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.4621. Min Act: -0.0000

Data Index: 1566761 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.3294. Min Act: -0.0000

Data Index: 1423778 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.1496. Min Act: -0.0000

Data Index: 1648458 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.3194. Min Act: -0.0000

Data Index: 1576036 (Python Code)

Max Activating Token Index: 152

Text #5

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.0922. Min Act: -0.0000

Data Index: 1575851 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.8805. Min Act: -0.0000

Data Index: 1575570 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.9553. Min Act: -0.0000

Data Index: 1569242 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.9575. Min Act: -0.0000

Data Index: 1410844 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.8726. Min Act: -0.0000

Data Index: 1509502 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.0368. Min Act: -0.0000

Data Index: 1491529 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 4.8229. Min Range: -4.8229

Max Act: 4.0062. Min Act: -0.0000

Data Index: 1625536 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.8289. Min Act: -0.0000

Data Index: 1370955 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.8192. Min Act: -0.0000

Data Index: 1373253 (Python Code)

Max Activating Token Index: 572

Text #14

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.7650. Min Act: -0.0000

Data Index: 1643165 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.6871. Min Act: -0.0000

Data Index: 1440932 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1607186 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.7443. Min Act: -0.0000

Data Index: 1425394 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.4309. Min Act: -0.0000

Data Index: 1456284 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 4.8229. Min Range: -4.8229

Max Act: 3.7550. Min Act: -0.0000

Data Index: 1649404 (Python Code)

Max Activating Token Index: 93