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

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

Neuron 4612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.6628. Min Act: -0.0000

Data Index: 164555 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1212219 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.6451. Min Act: -0.0000

Data Index: 479431 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.2695. Min Act: -0.0001

Data Index: 1323195 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.4582. Min Act: -0.0000

Data Index: 687225 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.3468. Min Act: -0.0001

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.5137. Min Act: -0.0001

Data Index: 150786 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.1559. Min Act: -0.0000

Data Index: 519775 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.3149. Min Act: -0.0001

Data Index: 389376 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.3849. Min Act: -0.0001

Data Index: 727007 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.4248. Min Act: -0.0000

Data Index: 385535 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.2076. Min Act: -0.0000

Data Index: 732500 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1211087 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.6607. Min Act: -0.0000

Data Index: 622777 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.3236. Min Act: -0.0001

Data Index: 295374 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.2081. Min Act: -0.0000

Data Index: 661435 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.4473. Min Act: -0.0001

Data Index: 584147 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1195671 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.2608. Min Act: -0.0000

Data Index: 787298 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.6628. Min Range: -1.6628

Max Act: 1.3130. Min Act: -0.0000

Data Index: 758302 (C4 (Web Text))

Max Activating Token Index: 495