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

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

Neuron 1221 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.8442. Min Act: -0.0000

Data Index: 265504 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.5471. Min Act: -0.0000

Data Index: 953533 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1586039 (Python Code)

Max Activating Token Index: 464

Text #3

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1013156 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.4358. Min Act: -0.0000

Data Index: 1543354 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.3557. Min Act: -0.0000

Data Index: 148877 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1508285 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.3927. Min Act: -0.0000

Data Index: 837336 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1374818 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1425060 (Python Code)

Max Activating Token Index: 142

Text #10

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2516. Min Act: -0.0000

Data Index: 899474 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.1601. Min Act: -0.0000

Data Index: 347468 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1325191 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1008349 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2058. Min Act: -0.0000

Data Index: 103984 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2580. Min Act: -0.0000

Data Index: 554884 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.2414. Min Act: -0.0000

Data Index: 926885 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.1338. Min Act: 0.0000

Data Index: 1638451 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1366401 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.1430. Min Act: -0.0000

Data Index: 5588 (C4 (Web Text))

Max Activating Token Index: 616