Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.5246. Min Act: -0.0001

Data Index: 1444871 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.3447. Min Act: -0.0001

Data Index: 1533304 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.3659. Min Act: -0.0001

Data Index: 1365438 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.3659. Min Act: -0.0001

Data Index: 1363298 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2910. Min Act: -0.0001

Data Index: 1653587 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2901. Min Act: -0.0001

Data Index: 1416194 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.3341. Min Act: -0.0001

Data Index: 1399060 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1482444 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2963. Min Act: -0.0001

Data Index: 1639159 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2746. Min Act: -0.0001

Data Index: 1412925 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1445328 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2445. Min Act: -0.0001

Data Index: 274019 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1500029 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1532034 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1471506 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1650002 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2435. Min Act: -0.0001

Data Index: 1535696 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2002. Min Act: -0.0001

Data Index: 1464609 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1426249 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 1.5246. Min Range: -1.5246

Max Act: 1.2360. Min Act: -0.0001

Data Index: 1361782 (Python Code)

Max Activating Token Index: 10