Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 870 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3660. Min Range: -1.3660

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1088507 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.3660. Min Range: -1.3660

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1072925 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.3660. Min Range: -1.3660

Max Act: 1.1252. Min Act: -0.0000

Data Index: 89380 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.3660. Min Range: -1.3660

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1101082 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.3660. Min Range: -1.3660

Max Act: 1.0530. Min Act: -0.0000

Data Index: 582606 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8733. Min Act: -0.0000

Data Index: 640764 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.9652. Min Act: -0.0000

Data Index: 270431 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.9121. Min Act: -0.0000

Data Index: 505045 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8648. Min Act: -0.0000

Data Index: 828493 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8104. Min Act: -0.0000

Data Index: 73181 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1153279 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1060027 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8068. Min Act: -0.0000

Data Index: 318647 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.7285. Min Act: -0.0000

Data Index: 876826 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.6811. Min Act: -0.0000

Data Index: 325794 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.7885. Min Act: -0.0000

Data Index: 796646 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1000621 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.8123. Min Act: -0.0000

Data Index: 853660 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.7740. Min Act: -0.0000

Data Index: 371712 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.3660. Min Range: -1.3660

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1090750 (C4 (Web Text))

Max Activating Token Index: 89