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

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

Neuron 5535 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: 3.8010. Min Range: -3.8010

Max Act: 3.5571. Min Act: -0.0000

Data Index: 1274559 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.8010. Min Act: -0.0000

Data Index: 753861 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.4370. Min Act: -0.0001

Data Index: 626068 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.2401. Min Act: -0.0001

Data Index: 429746 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.9679. Min Act: -0.0001

Data Index: 552795 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.0705. Min Act: -0.0001

Data Index: 38776 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.9391. Min Act: -0.0001

Data Index: 897628 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.8449. Min Act: -0.0001

Data Index: 19109 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.8480. Min Act: -0.0001

Data Index: 383389 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.9370. Min Act: -0.0001

Data Index: 193466 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.0413. Min Act: -0.0000

Data Index: 19336 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.2049. Min Act: -0.0001

Data Index: 928200 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.9788. Min Act: -0.0001

Data Index: 1344187 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.7559. Min Act: -0.0001

Data Index: 88143 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.8711. Min Act: -0.0001

Data Index: 461601 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.6998. Min Act: -0.0001

Data Index: 856201 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.5909. Min Act: -0.0001

Data Index: 1095167 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.7798. Min Act: -0.0001

Data Index: 291350 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.5959. Min Act: -0.0001

Data Index: 684317 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.8010. Min Range: -3.8010

Max Act: 2.2384. Min Act: -0.0001

Data Index: 981133 (C4 (Web Text))

Max Activating Token Index: 809