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

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

Neuron 602 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: 2.1871. Min Range: -2.1871

Max Act: 1.9934. Min Act: -0.0000

Data Index: 124040 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 2.1871. Min Range: -2.1871

Max Act: 2.1871. Min Act: -0.0000

Data Index: 193368 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6176. Min Act: -0.0000

Data Index: 658464 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 2.1871. Min Range: -2.1871

Max Act: 2.0290. Min Act: -0.0000

Data Index: 182900 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.7299. Min Act: -0.0001

Data Index: 382926 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.7638. Min Act: -0.0000

Data Index: 84843 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5695. Min Act: -0.0001

Data Index: 114412 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6595. Min Act: -0.0001

Data Index: 1163365 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1481268 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6170. Min Act: -0.0000

Data Index: 667485 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6614. Min Act: -0.0000

Data Index: 838177 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1295600 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5890. Min Act: -0.0000

Data Index: 608400 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5359. Min Act: -0.0001

Data Index: 451483 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1054971 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.3654. Min Act: -0.0000

Data Index: 462381 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1422840 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.5607. Min Act: -0.0000

Data Index: 865470 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.3477. Min Act: -0.0000

Data Index: 389081 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.1871. Min Range: -2.1871

Max Act: 1.4517. Min Act: -0.0000

Data Index: 465933 (C4 (Web Text))

Max Activating Token Index: 94