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

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

Neuron 5869 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0263. Min Range: -2.0263

Max Act: 2.0263. Min Act: -0.0000

Data Index: 1527700 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1480199 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1436121 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1527702 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.7910. Min Act: -0.0000

Data Index: 1541054 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1624807 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1486180 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8164. Min Act: -0.0000

Data Index: 1511647 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.7557. Min Act: -0.0000

Data Index: 1477168 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8555. Min Act: -0.0000

Data Index: 1474257 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8004. Min Act: -0.0000

Data Index: 1646595 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8841. Min Act: -0.0000

Data Index: 1528466 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.7267. Min Act: -0.0000

Data Index: 1498954 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8810. Min Act: -0.0000

Data Index: 1311165 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1058491 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1423745 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.6349. Min Act: -0.0000

Data Index: 1522126 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1616321 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 2.0263. Min Range: -2.0263

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1637215 (Python Code)

Max Activating Token Index: 30