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

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

Neuron 5125 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: 6.3056. Min Range: -6.3056

Max Act: 6.3056. Min Act: -0.0000

Data Index: 1448371 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.3722. Min Act: -0.0000

Data Index: 1452263 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.5103. Min Act: -0.0000

Data Index: 1455634 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.4652. Min Act: -0.0000

Data Index: 1623662 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.2490. Min Act: -0.0000

Data Index: 1624069 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.0516. Min Act: -0.0000

Data Index: 1493230 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 6.3056. Min Range: -6.3056

Max Act: 5.4296. Min Act: -0.0000

Data Index: 1629556 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.5967. Min Act: -0.0000

Data Index: 1399379 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.7316. Min Act: -0.0000

Data Index: 1551144 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.4649. Min Act: -0.0000

Data Index: 1503329 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.5981. Min Act: -0.0000

Data Index: 1428053 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.3338. Min Act: -0.0000

Data Index: 1531126 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.5707. Min Act: -0.0000

Data Index: 1402596 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.3728. Min Act: -0.0000

Data Index: 1421128 (Python Code)

Max Activating Token Index: 665

Text #14

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.1039. Min Act: -0.0000

Data Index: 1429091 (Python Code)

Max Activating Token Index: 588

Text #15

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.2579. Min Act: -0.0000

Data Index: 1598108 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.1501. Min Act: -0.0000

Data Index: 1360058 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.4527. Min Act: -0.0000

Data Index: 1503490 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 6.3056. Min Range: -6.3056

Max Act: 3.9338. Min Act: -0.0000

Data Index: 1511252 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 6.3056. Min Range: -6.3056

Max Act: 4.0945. Min Act: -0.0000

Data Index: 1360099 (Python Code)

Max Activating Token Index: 34