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

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

Neuron 48 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1449. Min Act: -0.0000

Data Index: 384084 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1466. Min Act: -0.0000

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1302. Min Act: -0.0001

Data Index: 427783 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1102928 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1566676 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1396961 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0894. Min Act: -0.0000

Data Index: 57479 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1445224 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1493234 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0795. Min Act: -0.0000

Data Index: 677776 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1594073 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1421802 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1535826 (Python Code)

Max Activating Token Index: 919

Text #14

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0900. Min Act: -0.0000

Data Index: 367515 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1566955 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0816. Min Act: -0.0000

Data Index: 740782 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1442640 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1007695 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1628325 (Python Code)

Max Activating Token Index: 850