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

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

Neuron 2004 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: 1.5049. Min Range: -1.5049

Max Act: 1.4673. Min Act: -0.0001

Data Index: 1568479 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4381. Min Act: -0.0001

Data Index: 1453354 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.5049. Min Act: -0.0001

Data Index: 1648031 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.5004. Min Act: -0.0001

Data Index: 1510402 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1526873 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2507. Min Act: -0.0001

Data Index: 1633116 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1404213 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1385076 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0240. Min Act: -0.0001

Data Index: 1462590 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0298. Min Act: -0.0001

Data Index: 1619266 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9961. Min Act: -0.0001

Data Index: 1391813 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0873. Min Act: -0.0001

Data Index: 902787 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0150. Min Act: -0.0001

Data Index: 956669 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9672. Min Act: -0.0001

Data Index: 439871 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9881. Min Act: -0.0001

Data Index: 206184 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0426. Min Act: -0.0001

Data Index: 1541445 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0010. Min Act: -0.0001

Data Index: 1519930 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9819. Min Act: -0.0001

Data Index: 715813 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9679. Min Act: -0.0001

Data Index: 1573189 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9142. Min Act: -0.0001

Data Index: 1563820 (Python Code)

Max Activating Token Index: 699