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

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

Neuron 3922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4985. Min Range: -3.4985

Max Act: 3.4985. Min Act: -0.0000

Data Index: 1321011 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.8915. Min Act: -0.0000

Data Index: 1100874 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.4985. Min Range: -3.4985

Max Act: 3.0074. Min Act: -0.0000

Data Index: 1018946 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.4985. Min Range: -3.4985

Max Act: 3.0163. Min Act: -0.0000

Data Index: 10945 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.8509. Min Act: -0.0000

Data Index: 1321319 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.6548. Min Act: -0.0000

Data Index: 560258 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.5023. Min Act: -0.0000

Data Index: 948656 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.3463. Min Act: -0.0000

Data Index: 1075597 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.2830. Min Act: -0.0000

Data Index: 259633 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.4089. Min Act: -0.0000

Data Index: 1066898 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.3888. Min Act: -0.0000

Data Index: 481783 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.2228. Min Act: -0.0000

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.2145. Min Act: -0.0000

Data Index: 109115 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1282755 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.3308. Min Act: -0.0000

Data Index: 1350213 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.5048. Min Act: -0.0000

Data Index: 1269884 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1174707 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.2342. Min Act: -0.0000

Data Index: 3454 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.1984. Min Act: -0.0000

Data Index: 701396 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.4985. Min Range: -3.4985

Max Act: 2.1962. Min Act: -0.0000

Data Index: 142980 (C4 (Web Text))

Max Activating Token Index: 933