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

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

Neuron 4505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.4990. Min Act: -0.0000

Data Index: 1606137 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.4439. Min Act: -0.0000

Data Index: 1521749 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.3658. Min Act: -0.0000

Data Index: 1474362 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1591028 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.0733. Min Act: -0.0000

Data Index: 1361358 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.0096. Min Act: -0.0000

Data Index: 1613029 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.1986. Min Act: -0.0000

Data Index: 1606196 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.4567. Min Act: -0.0000

Data Index: 1581507 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.1148. Min Act: -0.0000

Data Index: 1521804 (Python Code)

Max Activating Token Index: 753

Text #9

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1471701 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.9070. Min Act: -0.0000

Data Index: 1648791 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 2.4990. Min Range: -2.4990

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1406365 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.9928. Min Act: -0.0000

Data Index: 1420728 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1468866 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1465512 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1592963 (Python Code)

Max Activating Token Index: 296

Text #16

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.8947. Min Act: -0.0000

Data Index: 1533769 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.8819. Min Act: -0.0000

Data Index: 1604856 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1470707 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 2.4990. Min Range: -2.4990

Max Act: 1.6229. Min Act: -0.0000

Data Index: 1497788 (Python Code)

Max Activating Token Index: 335