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

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

Neuron 2254 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0290. Min Range: -1.0290

Max Act: 1.0290. Min Act: -0.0001

Data Index: 1189608 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.9584. Min Act: -0.0001

Data Index: 1357113 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1113675 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1308628 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8927. Min Act: -0.0001

Data Index: 656326 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8621. Min Act: -0.0001

Data Index: 370756 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8084. Min Act: -0.0001

Data Index: 735142 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7715. Min Act: -0.0001

Data Index: 30078 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8143. Min Act: -0.0000

Data Index: 51112 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7913. Min Act: -0.0000

Data Index: 170478 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7779. Min Act: -0.0000

Data Index: 370140 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7415. Min Act: -0.0001

Data Index: 814241 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7592. Min Act: -0.0001

Data Index: 823128 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7624. Min Act: -0.0000

Data Index: 124613 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1024252 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1006678 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1087584 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7333. Min Act: -0.0000

Data Index: 879601 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.6927. Min Act: -0.0001

Data Index: 260169 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7141. Min Act: -0.0000

Data Index: 903415 (C4 (Web Text))

Max Activating Token Index: 264