Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 464 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1629. Min Act: -0.0002

Data Index: 277344 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1643. Min Act: -0.0002

Data Index: 814122 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1565. Min Act: -0.0002

Data Index: 99092 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1683. Min Act: -0.0002

Data Index: 923900 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1540. Min Act: -0.0002

Data Index: 575800 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1489. Min Act: -0.0002

Data Index: 93182 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1435. Min Act: -0.0002

Data Index: 398188 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1529. Min Act: -0.0002

Data Index: 13320 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1489. Min Act: -0.0002

Data Index: 499681 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1475. Min Act: -0.0002

Data Index: 865765 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1345129 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1488. Min Act: -0.0002

Data Index: 90218 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1477. Min Act: -0.0002

Data Index: 43232 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1479. Min Act: -0.0002

Data Index: 714392 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1380. Min Act: -0.0002

Data Index: 3918 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1062533 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1219396 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1393. Min Act: -0.0002

Data Index: 8667 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1043276 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1361. Min Act: -0.0002

Data Index: 573670 (C4 (Web Text))

Max Activating Token Index: 88