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

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

Neuron 2343 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: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1131026 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0470. Min Act: -0.0000

Data Index: 981590 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1638170 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0510. Min Act: -0.0000

Data Index: 121481 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1281103 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0531. Min Act: -0.0000

Data Index: 856139 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1067957 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0477. Min Act: -0.0000

Data Index: 636987 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1618634 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1647451 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1208485 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0437. Min Act: -0.0000

Data Index: 384797 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0455. Min Act: -0.0000

Data Index: 985307 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0437. Min Act: -0.0000

Data Index: 815571 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0439. Min Act: -0.0000

Data Index: 666915 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0430. Min Act: -0.0000

Data Index: 842780 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0405. Min Act: -0.0000

Data Index: 136225 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1200229 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1430293 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0441. Min Act: -0.0000

Data Index: 776848 (C4 (Web Text))

Max Activating Token Index: 646