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

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

Neuron 4188 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.5576. Min Act: -0.0000

Data Index: 108504 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.4246. Min Act: -0.0000

Data Index: 923439 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.4431. Min Act: -0.0000

Data Index: 497300 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1618103 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.2946. Min Act: -0.0000

Data Index: 698067 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1242565 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1503397 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.2132. Min Act: -0.0000

Data Index: 598654 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1148952 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.1839. Min Act: -0.0000

Data Index: 909710 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.1457. Min Act: -0.0000

Data Index: 166986 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1469506 (Python Code)

Max Activating Token Index: 977

Text #12

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1157662 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0014. Min Act: -0.0000

Data Index: 185537 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1186375 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1552391 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1462863 (Python Code)

Max Activating Token Index: 674

Text #17

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0779. Min Act: -0.0000

Data Index: 104393 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.5576. Min Range: -1.5576

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1629688 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 1.5576. Min Range: -1.5576

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1239657 (C4 (Web Text))

Max Activating Token Index: 847