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

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

Neuron 1310 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: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1644387 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1090478 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2208. Min Act: -0.0000

Data Index: 178824 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1951. Min Act: -0.0000

Data Index: 515656 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1442330 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1418261 (Python Code)

Max Activating Token Index: 601

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1502171 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1469030 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1007083 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1591651 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1447781 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1555972 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1476921 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1455858 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1382405 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1639885 (Python Code)

Max Activating Token Index: 193

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1442276 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1552046 (Python Code)

Max Activating Token Index: 181