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

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

Neuron 4530 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.8017. Min Act: -0.0001

Data Index: 723748 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.4495. Min Act: -0.0001

Data Index: 953697 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.3659. Min Act: -0.0001

Data Index: 1131500 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.1494. Min Act: -0.0001

Data Index: 122102 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.1264. Min Act: -0.0000

Data Index: 663804 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.8851. Min Act: -0.0001

Data Index: 500475 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.1761. Min Act: -0.0001

Data Index: 190658 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.9964. Min Act: -0.0000

Data Index: 677363 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.0967. Min Act: -0.0000

Data Index: 292365 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.0281. Min Act: -0.0001

Data Index: 770491 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.0139. Min Act: -0.0001

Data Index: 481123 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.8458. Min Act: -0.0001

Data Index: 418577 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.7640. Min Act: -0.0000

Data Index: 194829 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.8727. Min Act: -0.0001

Data Index: 1130020 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.6737. Min Act: -0.0000

Data Index: 1285555 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.8232. Min Act: -0.0001

Data Index: 863040 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.8245. Min Act: -0.0001

Data Index: 3805 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.5017. Min Act: -0.0001

Data Index: 905456 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 4.8017. Min Range: -4.8017

Max Act: 4.1155. Min Act: -0.0001

Data Index: 559513 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 4.8017. Min Range: -4.8017

Max Act: 3.6301. Min Act: -0.0000

Data Index: 1012415 (C4 (Web Text))

Max Activating Token Index: 44