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

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

Neuron 4730 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: 5.4081. Min Range: -5.4081

Max Act: 5.4081. Min Act: -0.0001

Data Index: 46406 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 5.4081. Min Range: -5.4081

Max Act: 5.3531. Min Act: -0.0001

Data Index: 1341041 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.8911. Min Act: -0.0001

Data Index: 224971 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.3696. Min Act: -0.0001

Data Index: 385470 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.5480. Min Act: -0.0001

Data Index: 559630 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6821. Min Act: -0.0001

Data Index: 454688 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.4720. Min Act: -0.0001

Data Index: 115118 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.3446. Min Act: -0.0001

Data Index: 974840 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.5497. Min Act: -0.0001

Data Index: 830342 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6792. Min Act: -0.0001

Data Index: 727262 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6799. Min Act: -0.0001

Data Index: 876459 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.4540. Min Act: -0.0001

Data Index: 545144 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.1176. Min Act: -0.0001

Data Index: 581228 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.4013. Min Act: -0.0001

Data Index: 154568 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.2168. Min Act: -0.0000

Data Index: 96445 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.1838. Min Act: -0.0001

Data Index: 472484 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.3396. Min Act: -0.0001

Data Index: 299259 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.0764. Min Act: -0.0001

Data Index: 723832 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.1989. Min Act: -0.0000

Data Index: 379359 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.0443. Min Act: -0.0000

Data Index: 1332029 (C4 (Web Text))

Max Activating Token Index: 392