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

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

Neuron 2774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.3218. Min Act: -0.0000

Data Index: 681119 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1104379 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1193913 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2403. Min Act: -0.0000

Data Index: 707901 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2073. Min Act: -0.0000

Data Index: 424628 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2021. Min Act: -0.0000

Data Index: 783267 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2197. Min Act: -0.0000

Data Index: 918862 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2149. Min Act: -0.0000

Data Index: 730513 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1985. Min Act: -0.0000

Data Index: 788301 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1585308 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1417079 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1299512 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1196584 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2030. Min Act: -0.0000

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.2042. Min Act: -0.0000

Data Index: 412848 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1862. Min Act: -0.0000

Data Index: 841374 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1897. Min Act: -0.0000

Data Index: 147147 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1415516 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1956. Min Act: -0.0000

Data Index: 929485 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.3218. Min Range: -0.3218

Max Act: 0.1868. Min Act: -0.0000

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 409