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

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

Neuron 874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0479. Min Range: -3.0479

Max Act: 3.0479. Min Act: -0.0000

Data Index: 184351 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.8977. Min Act: -0.0000

Data Index: 265639 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.7337. Min Act: -0.0000

Data Index: 65767 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.5484. Min Act: -0.0000

Data Index: 146590 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.5645. Min Act: -0.0000

Data Index: 603703 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.5500. Min Act: -0.0000

Data Index: 148153 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.4037. Min Act: -0.0000

Data Index: 716732 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.3719. Min Act: -0.0000

Data Index: 719838 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.3455. Min Act: -0.0000

Data Index: 1051562 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.2795. Min Act: -0.0000

Data Index: 686172 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.2619. Min Act: -0.0000

Data Index: 321701 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1203. Min Act: -0.0000

Data Index: 156039 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.2178. Min Act: -0.0000

Data Index: 24415 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1634. Min Act: -0.0000

Data Index: 927887 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1893. Min Act: -0.0000

Data Index: 974709 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1744. Min Act: -0.0000

Data Index: 999320 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1796. Min Act: -0.0000

Data Index: 337253 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 3.0479. Min Range: -3.0479

Max Act: 1.9510. Min Act: -0.0000

Data Index: 81645 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.1544. Min Act: -0.0000

Data Index: 155751 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 3.0479. Min Range: -3.0479

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1078533 (C4 (Web Text))

Max Activating Token Index: 4