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

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

Neuron 4695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.8915. Min Act: -0.0000

Data Index: 1140879 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1109361 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.3580. Min Act: -0.0000

Data Index: 30255 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.3420. Min Act: -0.0000

Data Index: 1269598 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.3302. Min Act: -0.0000

Data Index: 97401 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.2237. Min Act: -0.0000

Data Index: 428606 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.1799. Min Act: -0.0000

Data Index: 491505 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.1431. Min Act: -0.0000

Data Index: 1101508 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 3.8915. Min Range: -3.8915

Max Act: 2.9930. Min Act: -0.0000

Data Index: 1305698 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.8915. Min Range: -3.8915

Max Act: 2.9529. Min Act: -0.0000

Data Index: 385187 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0813. Min Act: -0.0000

Data Index: 962453 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0799. Min Act: -0.0000

Data Index: 1294004 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0595. Min Act: -0.0000

Data Index: 863466 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0336. Min Act: -0.0000

Data Index: 535 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0267. Min Act: -0.0000

Data Index: 561892 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.8915. Min Range: -3.8915

Max Act: 2.9975. Min Act: -0.0000

Data Index: 184023 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.8915. Min Range: -3.8915

Max Act: 2.8734. Min Act: -0.0000

Data Index: 473159 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 3.8915. Min Range: -3.8915

Max Act: 2.9601. Min Act: -0.0000

Data Index: 625269 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.0869. Min Act: -0.0000

Data Index: 981203 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 3.8915. Min Range: -3.8915

Max Act: 3.2409. Min Act: -0.0000

Data Index: 675525 (C4 (Web Text))

Max Activating Token Index: 863