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

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

Neuron 268 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: 1.0605. Min Range: -1.0605

Max Act: 0.9758. Min Act: -0.0000

Data Index: 770544 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9437. Min Act: -0.0000

Data Index: 679014 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0605. Min Act: -0.0000

Data Index: 100833 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1650754 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1488354 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9156. Min Act: -0.0000

Data Index: 683882 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9233. Min Act: -0.0000

Data Index: 710309 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1507490 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8484. Min Act: -0.0000

Data Index: 553219 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8363. Min Act: -0.0000

Data Index: 382053 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1486724 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1524761 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1370577 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7892. Min Act: -0.0000

Data Index: 374552 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8239. Min Act: -0.0000

Data Index: 689941 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7793. Min Act: -0.0000

Data Index: 443884 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1483557 (Python Code)

Max Activating Token Index: 891

Text #17

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1391773 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1570844 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1039439 (C4 (Web Text))

Max Activating Token Index: 538