Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3937 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1469726 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5805. Min Act: -0.0001

Data Index: 1631646 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1048583 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1476432 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1561159 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5300. Min Act: -0.0001

Data Index: 672968 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5463. Min Act: -0.0001

Data Index: 211733 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1272253 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5418. Min Act: -0.0001

Data Index: 1258417 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5033. Min Act: -0.0001

Data Index: 126087 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4876. Min Act: -0.0001

Data Index: 1204048 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4991. Min Act: -0.0001

Data Index: 468678 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1524494 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5062. Min Act: -0.0001

Data Index: 917044 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4911. Min Act: -0.0001

Data Index: 520797 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1535049 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1419252 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1382752 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4781. Min Act: -0.0001

Data Index: 925707 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4781. Min Act: -0.0001

Data Index: 860479 (C4 (Web Text))

Max Activating Token Index: 262