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

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

Neuron 3716 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: 4.4275. Min Range: -4.4275

Max Act: 4.4275. Min Act: -0.0000

Data Index: 889308 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.8611. Min Act: -0.0000

Data Index: 1131242 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.8399. Min Act: -0.0000

Data Index: 249266 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 4.4275. Min Range: -4.4275

Max Act: 4.0511. Min Act: -0.0000

Data Index: 1191466 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.5907. Min Act: -0.0000

Data Index: 346408 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.3848. Min Act: -0.0000

Data Index: 837182 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.3774. Min Act: -0.0000

Data Index: 297026 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.3985. Min Act: -0.0000

Data Index: 160198 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.5473. Min Act: -0.0000

Data Index: 739725 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.3206. Min Act: -0.0000

Data Index: 104143 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.2936. Min Act: -0.0000

Data Index: 697045 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.2523. Min Act: -0.0000

Data Index: 547664 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.7762. Min Act: -0.0000

Data Index: 1078675 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.9549. Min Act: -0.0000

Data Index: 356051 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.9216. Min Act: -0.0000

Data Index: 917745 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 4.4275. Min Range: -4.4275

Max Act: 3.0595. Min Act: -0.0000

Data Index: 3040 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.7653. Min Act: -0.0000

Data Index: 593184 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.8714. Min Act: -0.0000

Data Index: 290932 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.7317. Min Act: -0.0000

Data Index: 160495 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 4.4275. Min Range: -4.4275

Max Act: 2.8761. Min Act: -0.0000

Data Index: 1221611 (C4 (Web Text))

Max Activating Token Index: 113