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

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

Neuron 3300 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: 0.7672. Min Range: -0.7672

Max Act: 0.7672. Min Act: -0.0000

Data Index: 371516 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6972. Min Act: -0.0000

Data Index: 788973 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7361. Min Act: -0.0000

Data Index: 647447 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7435. Min Act: -0.0000

Data Index: 74741 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7512. Min Act: -0.0000

Data Index: 339409 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1015749 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7263. Min Act: -0.0000

Data Index: 403264 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6538. Min Act: -0.0000

Data Index: 468840 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1575540 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7156. Min Act: -0.0000

Data Index: 6644 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7244. Min Act: -0.0000

Data Index: 176663 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6967. Min Act: -0.0000

Data Index: 938721 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.7062. Min Act: -0.0000

Data Index: 598800 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6270. Min Act: -0.0000

Data Index: 702609 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1355934 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6460. Min Act: -0.0000

Data Index: 590540 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6558. Min Act: -0.0000

Data Index: 550579 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1061934 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1101015 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.7672. Min Range: -0.7672

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1074058 (C4 (Web Text))

Max Activating Token Index: 900