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

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

Neuron 5248 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.7514. Min Act: -0.0001

Data Index: 174885 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.8678. Min Act: -0.0000

Data Index: 117681 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.4722. Min Act: -0.0000

Data Index: 996989 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.4668. Min Act: -0.0000

Data Index: 148394 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.4231. Min Act: -0.0001

Data Index: 1083344 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2634. Min Act: -0.0000

Data Index: 1227399 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3700. Min Act: -0.0001

Data Index: 557168 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3108. Min Act: -0.0001

Data Index: 355781 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2742. Min Act: -0.0000

Data Index: 1309012 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.1668. Min Act: -0.0000

Data Index: 1220426 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2343. Min Act: -0.0001

Data Index: 273993 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.0194. Min Act: -0.0001

Data Index: 1300271 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.1071. Min Act: -0.0000

Data Index: 1073268 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.3056. Min Act: -0.0000

Data Index: 844398 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.1675. Min Act: -0.0000

Data Index: 992418 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2721. Min Act: -0.0001

Data Index: 1161382 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.1495. Min Act: -0.0000

Data Index: 1070953 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.8678. Min Range: -2.8678

Max Act: 1.9876. Min Act: -0.0000

Data Index: 603663 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 2.8678. Min Range: -2.8678

Max Act: 2.2033. Min Act: -0.0000

Data Index: 441348 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.8678. Min Range: -2.8678

Max Act: 1.9553. Min Act: -0.0001

Data Index: 257870 (C4 (Web Text))

Max Activating Token Index: 237