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

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

Neuron 4739 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.8998. Min Act: -0.0000

Data Index: 467595 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.5827. Min Act: -0.0000

Data Index: 900149 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.8330. Min Act: -0.0000

Data Index: 1155961 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.5891. Min Act: -0.0000

Data Index: 424913 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1153248 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.5126. Min Act: -0.0000

Data Index: 503552 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.4804. Min Act: -0.0000

Data Index: 8504 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.2773. Min Act: -0.0000

Data Index: 725518 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.2042. Min Act: -0.0000

Data Index: 1158687 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.4940. Min Act: -0.0000

Data Index: 984153 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.3074. Min Act: -0.0000

Data Index: 1250730 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.2718. Min Act: -0.0000

Data Index: 767977 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.4020. Min Act: -0.0000

Data Index: 400259 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.2112. Min Act: -0.0000

Data Index: 328269 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1176477 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.1662. Min Act: -0.0000

Data Index: 373728 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.1259. Min Act: -0.0000

Data Index: 1268028 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.1339. Min Act: -0.0000

Data Index: 532782 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.0977. Min Act: -0.0000

Data Index: 290948 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.8998. Min Range: -3.8998

Max Act: 3.1108. Min Act: -0.0000

Data Index: 1269938 (C4 (Web Text))

Max Activating Token Index: 841