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

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

Neuron 4567 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1604111 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1563699 (Python Code)

Max Activating Token Index: 773

Text #2

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1374821 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1566605 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1506080 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1398231 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1587898 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1454574 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1448391 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1534027 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1451654 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1653254 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1621823 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1462586 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1362877 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1609215 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1402742 (Python Code)

Max Activating Token Index: 935

Text #17

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1365890 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1641746 (Python Code)

Max Activating Token Index: 357

Text #19

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1561041 (Python Code)

Max Activating Token Index: 659