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

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

Neuron 5362 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: 1.3557. Min Range: -1.3557

Max Act: 1.3557. Min Act: -0.0001

Data Index: 342179 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3426. Min Act: -0.0001

Data Index: 670785 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.0810. Min Act: -0.0001

Data Index: 375828 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.0672. Min Act: -0.0001

Data Index: 1123965 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.0153. Min Act: -0.0001

Data Index: 434970 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1541315 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8781. Min Act: -0.0001

Data Index: 51693 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8506. Min Act: -0.0001

Data Index: 1430724 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9150. Min Act: -0.0001

Data Index: 713735 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9032. Min Act: -0.0001

Data Index: 44592 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8943. Min Act: -0.0001

Data Index: 786813 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1158480 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8569. Min Act: -0.0001

Data Index: 1171045 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8382. Min Act: -0.0001

Data Index: 1266192 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8421. Min Act: -0.0001

Data Index: 82991 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.7963. Min Act: -0.0001

Data Index: 1329108 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.7714. Min Act: -0.0001

Data Index: 821709 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1611249 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8211. Min Act: -0.0001

Data Index: 616789 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.7939. Min Act: -0.0001

Data Index: 861391 (C4 (Web Text))

Max Activating Token Index: 854