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

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

Neuron 4335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7803. Min Act: -0.0002

Data Index: 1624135 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7869. Min Act: -0.0002

Data Index: 1634757 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7638. Min Act: -0.0002

Data Index: 1573882 (Python Code)

Max Activating Token Index: 743

Text #3

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7416. Min Act: -0.0002

Data Index: 1475639 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6232. Min Act: -0.0002

Data Index: 1528841 (Python Code)

Max Activating Token Index: 861

Text #5

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6335. Min Act: -0.0002

Data Index: 1624354 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5991. Min Act: -0.0002

Data Index: 1427829 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.4618. Min Act: -0.0002

Data Index: 1568269 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5019. Min Act: -0.0002

Data Index: 1379349 (Python Code)

Max Activating Token Index: 253

Text #9

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6161. Min Act: -0.0002

Data Index: 1535142 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.4525. Min Act: -0.0002

Data Index: 1372986 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6544. Min Act: -0.0002

Data Index: 1424129 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5591. Min Act: -0.0002

Data Index: 1521275 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5079. Min Act: -0.0002

Data Index: 1528850 (Python Code)

Max Activating Token Index: 929

Text #14

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3731. Min Act: -0.0002

Data Index: 1423770 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5155. Min Act: -0.0002

Data Index: 1374530 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5108. Min Act: -0.0002

Data Index: 1536613 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.4773. Min Act: -0.0002

Data Index: 1474728 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3907. Min Act: -0.0002

Data Index: 1604583 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5099. Min Act: -0.0002

Data Index: 1367250 (Python Code)

Max Activating Token Index: 408