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

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

Neuron 52 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.2967. Min Act: 0.0000

Data Index: 1463448 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.2735. Min Act: -0.0000

Data Index: 1432327 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.6204. Min Act: -0.0000

Data Index: 1576102 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.7082. Min Act: -0.0000

Data Index: 1370797 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1645176 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.6594. Min Act: -0.0000

Data Index: 1445655 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.5747. Min Act: -0.0000

Data Index: 1374600 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.6454. Min Act: -0.0000

Data Index: 1579915 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.3690. Min Act: -0.0000

Data Index: 1477753 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.4634. Min Act: -0.0000

Data Index: 1543165 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.4655. Min Act: -0.0000

Data Index: 1426347 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1385769 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.4492. Min Act: 0.0000

Data Index: 1461218 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.4238. Min Act: -0.0000

Data Index: 1639797 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.5303. Min Act: -0.0000

Data Index: 1470283 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.3030. Min Act: -0.0000

Data Index: 1647742 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1635343 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.1463. Min Act: -0.0000

Data Index: 1616252 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.2470. Min Act: -0.0000

Data Index: 1631871 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 3.2967. Min Range: -3.2967

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1526269 (Python Code)

Max Activating Token Index: 212