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

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

Neuron 3085 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4668. Min Act: -0.0001

Data Index: 489338 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.3573. Min Act: -0.0001

Data Index: 486305 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.2962. Min Act: -0.0001

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4325. Min Act: -0.0001

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.3592. Min Act: -0.0001

Data Index: 828921 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1985. Min Act: -0.0001

Data Index: 779820 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.2625. Min Act: -0.0001

Data Index: 858033 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.2599. Min Act: -0.0001

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1441. Min Act: -0.0001

Data Index: 130618 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1496. Min Act: -0.0001

Data Index: 181645 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.2205. Min Act: -0.0001

Data Index: 994233 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1087. Min Act: -0.0001

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.0912. Min Act: -0.0001

Data Index: 759368 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1548. Min Act: -0.0001

Data Index: 1195632 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.0673. Min Act: -0.0001

Data Index: 1024123 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.0545. Min Act: -0.0001

Data Index: 1290946 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1908. Min Act: -0.0001

Data Index: 275951 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.0406. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.0232. Min Act: -0.0001

Data Index: 113701 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.1654. Min Act: -0.0001

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 802