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

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

Neuron 143 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1126982 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7954. Min Act: -0.0000

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1260770 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1285850 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1392060 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1638457 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1556689 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5025. Min Act: -0.0001

Data Index: 1562528 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1439213 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5690. Min Act: -0.0000

Data Index: 192224 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5520. Min Act: -0.0000

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1396861 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5303. Min Act: -0.0000

Data Index: 358063 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1472839 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1097084 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5017. Min Act: 0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1406838 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5306. Min Act: -0.0000

Data Index: 291514 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.4944. Min Act: -0.0001

Data Index: 1365765 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1534962 (Python Code)

Max Activating Token Index: 234