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

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

Neuron 3874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.4674. Min Act: -0.0000

Data Index: 1554206 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.0453. Min Act: -0.0000

Data Index: 1414023 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.2268. Min Act: -0.0000

Data Index: 1369062 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.3175. Min Act: -0.0000

Data Index: 1557721 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1541. Min Act: -0.0000

Data Index: 1508082 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1657. Min Act: -0.0000

Data Index: 1423244 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1589. Min Act: -0.0000

Data Index: 1581248 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1542. Min Act: -0.0000

Data Index: 1543973 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1445. Min Act: -0.0000

Data Index: 1506825 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.0371. Min Act: -0.0000

Data Index: 1563605 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.9134. Min Act: -0.0000

Data Index: 1524281 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1861. Min Act: -0.0000

Data Index: 1465639 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 3.4674. Min Range: -3.4674

Max Act: 3.1772. Min Act: -0.0000

Data Index: 1583124 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.8957. Min Act: -0.0000

Data Index: 1563828 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.7806. Min Act: -0.0000

Data Index: 1415940 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.7485. Min Act: -0.0000

Data Index: 1497548 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.8293. Min Act: -0.0000

Data Index: 1545883 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.9834. Min Act: -0.0000

Data Index: 1413576 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.9216. Min Act: -0.0000

Data Index: 1612862 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 3.4674. Min Range: -3.4674

Max Act: 2.5668. Min Act: -0.0000

Data Index: 1566347 (Python Code)

Max Activating Token Index: 228