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

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

Neuron 4262 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.2635. Min Act: -0.0000

Data Index: 1519735 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1623522 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1510560 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.6289. Min Act: -0.0000

Data Index: 1522354 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.5896. Min Act: -0.0000

Data Index: 1372838 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.1222. Min Act: -0.0000

Data Index: 1258706 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1419495 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1502504 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.1550. Min Act: -0.0000

Data Index: 1492230 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.7217. Min Act: -0.0000

Data Index: 1408425 (Python Code)

Max Activating Token Index: 323

Text #10

Max Range: 3.2635. Min Range: -3.2635

Max Act: 2.1942. Min Act: -0.0000

Data Index: 944606 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1608148 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.8249. Min Act: -0.0000

Data Index: 1628104 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1615056 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1655126 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.8925. Min Act: -0.0000

Data Index: 1189830 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.8949. Min Act: -0.0000

Data Index: 1560701 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1612306 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1189558 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.2635. Min Range: -3.2635

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1504587 (Python Code)

Max Activating Token Index: 968