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

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

Neuron 6120 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0871. Min Range: -6.0871

Max Act: 6.0871. Min Act: -0.0000

Data Index: 386307 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 6.0871. Min Range: -6.0871

Max Act: 5.4766. Min Act: -0.0000

Data Index: 569109 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 6.0871. Min Range: -6.0871

Max Act: 5.3381. Min Act: -0.0000

Data Index: 825461 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 6.0871. Min Range: -6.0871

Max Act: 5.4894. Min Act: -0.0000

Data Index: 972398 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 6.0871. Min Range: -6.0871

Max Act: 5.1582. Min Act: -0.0000

Data Index: 820257 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 6.0871. Min Range: -6.0871

Max Act: 5.1160. Min Act: -0.0000

Data Index: 222648 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.9306. Min Act: -0.0000

Data Index: 558471 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.6603. Min Act: -0.0000

Data Index: 347532 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.5682. Min Act: -0.0000

Data Index: 1252351 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.4879. Min Act: -0.0000

Data Index: 423634 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.4206. Min Act: -0.0000

Data Index: 1192278 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.5720. Min Act: -0.0000

Data Index: 617474 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.1601. Min Act: -0.0000

Data Index: 986857 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.3203. Min Act: -0.0000

Data Index: 1306477 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 6.0871. Min Range: -6.0871

Max Act: 3.8830. Min Act: -0.0000

Data Index: 772585 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.0059. Min Act: -0.0000

Data Index: 849772 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 6.0871. Min Range: -6.0871

Max Act: 3.9861. Min Act: -0.0000

Data Index: 1043680 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 6.0871. Min Range: -6.0871

Max Act: 3.7648. Min Act: -0.0000

Data Index: 179483 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 6.0871. Min Range: -6.0871

Max Act: 3.9428. Min Act: -0.0000

Data Index: 721676 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 6.0871. Min Range: -6.0871

Max Act: 4.0786. Min Act: -0.0000

Data Index: 605280 (C4 (Web Text))

Max Activating Token Index: 308