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

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

Neuron 477 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.2354. Min Act: -0.0000

Data Index: 1177925 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.5650. Min Act: -0.0000

Data Index: 285093 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0324. Min Act: -0.0000

Data Index: 568708 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.7667. Min Act: -0.0000

Data Index: 284875 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.4963. Min Act: -0.0000

Data Index: 1360053 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.5931. Min Act: -0.0000

Data Index: 1521926 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.5788. Min Act: -0.0000

Data Index: 619870 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1037455 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.5366. Min Act: -0.0000

Data Index: 206612 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.3505. Min Act: -0.0000

Data Index: 1105313 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.3308. Min Act: -0.0000

Data Index: 487470 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.4169. Min Act: -0.0000

Data Index: 239144 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.3835. Min Act: -0.0000

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.2045. Min Act: -0.0000

Data Index: 381442 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.2111. Min Act: -0.0000

Data Index: 681267 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.3012. Min Act: -0.0000

Data Index: 1008446 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.1688. Min Act: -0.0000

Data Index: 646639 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.2165. Min Act: -0.0000

Data Index: 693276 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.2265. Min Act: -0.0000

Data Index: 537950 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 3.2354. Min Range: -3.2354

Max Act: 2.2248. Min Act: -0.0000

Data Index: 205780 (C4 (Web Text))

Max Activating Token Index: 726