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

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

Neuron 2796 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.8335. Min Act: -0.0000

Data Index: 215478 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7500. Min Act: -0.0000

Data Index: 887535 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6711. Min Act: -0.0000

Data Index: 105671 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5148. Min Act: -0.0000

Data Index: 882420 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5717. Min Act: -0.0000

Data Index: 26881 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4013. Min Act: -0.0000

Data Index: 219508 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5060. Min Act: -0.0000

Data Index: 144908 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1035821 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1290380 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4478. Min Act: -0.0000

Data Index: 617735 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4517. Min Act: -0.0000

Data Index: 67038 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5136. Min Act: -0.0000

Data Index: 292205 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4783. Min Act: -0.0000

Data Index: 264134 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4612. Min Act: -0.0000

Data Index: 442844 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4538. Min Act: -0.0000

Data Index: 36420 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4293. Min Act: -0.0000

Data Index: 620634 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4741. Min Act: -0.0000

Data Index: 637863 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4389. Min Act: -0.0000

Data Index: 590096 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.4294. Min Act: -0.0000

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 891