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

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

Neuron 3630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1464217 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1469994 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1565267 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1643425 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1414478 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1366109 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1582997 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1505742 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1444717 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1557112 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1537202 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1610921 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1631028 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1410209 (Python Code)

Max Activating Token Index: 695

Text #14

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1058828 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1590065 (Python Code)

Max Activating Token Index: 380

Text #16

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1478619 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1628994 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1634228 (Python Code)

Max Activating Token Index: 334

Text #19

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1590725 (Python Code)

Max Activating Token Index: 453