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

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

Neuron 4324 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.9080. Min Act: -0.0000

Data Index: 789657 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.9993. Min Act: -0.0000

Data Index: 831435 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 3.0672. Min Range: -3.0672

Max Act: 3.0672. Min Act: -0.0000

Data Index: 1417714 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.8997. Min Act: -0.0000

Data Index: 1369410 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.5684. Min Act: -0.0000

Data Index: 1000388 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.6138. Min Act: -0.0000

Data Index: 1513471 (Python Code)

Max Activating Token Index: 588

Text #6

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.7159. Min Act: -0.0000

Data Index: 233485 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.6942. Min Act: -0.0000

Data Index: 820125 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.5097. Min Act: -0.0000

Data Index: 1582869 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.5134. Min Act: -0.0000

Data Index: 1622229 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.4574. Min Act: -0.0000

Data Index: 1497741 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.9804. Min Act: -0.0000

Data Index: 1218270 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.7123. Min Act: -0.0000

Data Index: 347769 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1474918 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1376010 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1378668 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.3385. Min Act: -0.0000

Data Index: 1480336 (Python Code)

Max Activating Token Index: 741

Text #17

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1421912 (Python Code)

Max Activating Token Index: 718

Text #18

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.2658. Min Act: -0.0000

Data Index: 1643516 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 3.0672. Min Range: -3.0672

Max Act: 2.2266. Min Act: -0.0000

Data Index: 1363231 (Python Code)

Max Activating Token Index: 510