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

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

Neuron 2716 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: 2.5677. Min Range: -2.5677

Max Act: 2.5677. Min Act: -0.0000

Data Index: 1629211 (Python Code)

Max Activating Token Index: 970

Text #1

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.2935. Min Act: -0.0000

Data Index: 1527808 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.3620. Min Act: -0.0000

Data Index: 1490640 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.1276. Min Act: -0.0000

Data Index: 1637706 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1606998 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.2227. Min Act: -0.0000

Data Index: 721808 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1585346 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 2.5677. Min Range: -2.5677

Max Act: 2.0377. Min Act: -0.0000

Data Index: 1491995 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1395828 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.8337. Min Act: -0.0000

Data Index: 1563989 (Python Code)

Max Activating Token Index: 970

Text #10

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1522929 (Python Code)

Max Activating Token Index: 790

Text #11

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.8953. Min Act: 0.0000

Data Index: 1528038 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.9591. Min Act: -0.0000

Data Index: 1478520 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.6823. Min Act: -0.0000

Data Index: 788402 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.6968. Min Act: -0.0000

Data Index: 1390373 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.6633. Min Act: -0.0000

Data Index: 1018607 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.7406. Min Act: -0.0000

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.6166. Min Act: -0.0000

Data Index: 1464753 (Python Code)

Max Activating Token Index: 242

Text #18

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1454606 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.5677. Min Range: -2.5677

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1394663 (Python Code)

Max Activating Token Index: 518