Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.9177. Min Act: -0.0000

Data Index: 1367030 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1628965 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.6711. Min Act: -0.0000

Data Index: 1420260 (Python Code)

Max Activating Token Index: 813

Text #3

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.4717. Min Act: -0.0000

Data Index: 1564811 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.4342. Min Act: -0.0000

Data Index: 1618670 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5266. Min Act: -0.0000

Data Index: 1629458 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3077. Min Act: -0.0000

Data Index: 1560577 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.2763. Min Act: -0.0000

Data Index: 1600024 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.2614. Min Act: -0.0000

Data Index: 1610065 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3123. Min Act: -0.0000

Data Index: 1365267 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.9633. Min Act: -0.0000

Data Index: 1442770 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.0194. Min Act: -0.0000

Data Index: 1551522 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1652343 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.9955. Min Act: -0.0000

Data Index: 1382984 (Python Code)

Max Activating Token Index: 533

Text #14

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.8391. Min Act: -0.0000

Data Index: 1413505 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1565513 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.9388. Min Act: -0.0000

Data Index: 1547064 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1429712 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.8412. Min Act: -0.0000

Data Index: 1518898 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 2.9727. Min Range: -2.9727

Max Act: 1.9423. Min Act: -0.0000

Data Index: 1466199 (Python Code)

Max Activating Token Index: 411