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

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

Neuron 1999 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: 4.9090. Min Range: -4.9090

Max Act: 4.9090. Min Act: -0.0000

Data Index: 1327444 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.8021. Min Act: -0.0000

Data Index: 630439 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.3964. Min Act: -0.0000

Data Index: 1034104 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1856. Min Act: -0.0000

Data Index: 767640 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.2879. Min Act: -0.0000

Data Index: 1196892 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1498. Min Act: -0.0000

Data Index: 402671 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1049120 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.0199. Min Act: -0.0000

Data Index: 38453 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1318. Min Act: -0.0000

Data Index: 371512 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1168. Min Act: -0.0000

Data Index: 760361 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.0193. Min Act: -0.0000

Data Index: 1325135 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1108. Min Act: -0.0000

Data Index: 130752 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.0562. Min Act: -0.0000

Data Index: 707323 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.0059. Min Act: -0.0000

Data Index: 399348 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.1168. Min Act: -0.0000

Data Index: 531598 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 4.9090. Min Range: -4.9090

Max Act: 1.8880. Min Act: -0.0000

Data Index: 3273 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 4.9090. Min Range: -4.9090

Max Act: 2.2129. Min Act: -0.0000

Data Index: 1379685 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 4.9090. Min Range: -4.9090

Max Act: 1.7237. Min Act: -0.0000

Data Index: 974419 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 4.9090. Min Range: -4.9090

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1258410 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.9090. Min Range: -4.9090

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1544670 (Python Code)

Max Activating Token Index: 187