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

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

Neuron 726 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: 0.9309. Min Range: -0.9309

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1445991 (Python Code)

Max Activating Token Index: 360

Text #1

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1533282 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1409583 (Python Code)

Max Activating Token Index: 904

Text #3

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1431214 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8097. Min Act: -0.0001

Data Index: 1582133 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1541870 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1634844 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8492. Min Act: -0.0001

Data Index: 1455396 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8050. Min Act: -0.0001

Data Index: 1455111 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1449303 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7723. Min Act: -0.0001

Data Index: 82899 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1490683 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1426854 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1521263 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1459611 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1404899 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1126300 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1375056 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7552. Min Act: -0.0001

Data Index: 1368180 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1468287 (Python Code)

Max Activating Token Index: 977