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

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

Neuron 4527 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.7028. Min Act: -0.0000

Data Index: 1425295 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1631789 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1503769 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1458719 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1395232 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1580966 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1369596 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1583036 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1476074 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1507694 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1412321 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3102. Min Act: -0.0000

Data Index: 1371743 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1608469 (Python Code)

Max Activating Token Index: 358

Text #13

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1364672 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1468130 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1653945 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1482610 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1516421 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1475264 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 1.7028. Min Range: -1.7028

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1509857 (Python Code)

Max Activating Token Index: 8