Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0379. Min Range: -1.0379

Max Act: 1.0191. Min Act: -0.0000

Data Index: 690115 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.0379. Min Range: -1.0379

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1259986 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.0379. Min Range: -1.0379

Max Act: 1.0379. Min Act: -0.0000

Data Index: 216757 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1259945 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.0379. Min Range: -1.0379

Max Act: 1.0155. Min Act: -0.0000

Data Index: 422980 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1116198 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1100314 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9554. Min Act: -0.0000

Data Index: 570240 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9286. Min Act: -0.0000

Data Index: 477311 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9481. Min Act: -0.0000

Data Index: 342176 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9122. Min Act: -0.0000

Data Index: 440232 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9223. Min Act: -0.0000

Data Index: 206263 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9330. Min Act: -0.0000

Data Index: 564647 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9101. Min Act: -0.0000

Data Index: 189483 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.8591. Min Act: -0.0000

Data Index: 884823 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1116983 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.8235. Min Act: -0.0000

Data Index: 914833 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.9015. Min Act: -0.0000

Data Index: 701610 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.8449. Min Act: -0.0000

Data Index: 576681 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1235762 (C4 (Web Text))

Max Activating Token Index: 615