Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4539 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0713. Min Range: -2.0713

Max Act: 2.0713. Min Act: 0.0000

Data Index: 439196 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.3930. Min Act: -0.0000

Data Index: 351948 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.3573. Min Act: 0.0000

Data Index: 1124460 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.2426. Min Act: 0.0000

Data Index: 339523 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.1964. Min Act: 0.0000

Data Index: 383972 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1218825 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0545. Min Act: -0.0000

Data Index: 813811 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.1185. Min Act: 0.0000

Data Index: 1117584 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.1611. Min Act: -0.0000

Data Index: 431357 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0797. Min Act: 0.0000

Data Index: 313219 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0741. Min Act: 0.0000

Data Index: 988372 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1140642 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0753. Min Act: -0.0000

Data Index: 916527 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0743. Min Act: -0.0000

Data Index: 850657 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1074110 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0018. Min Act: 0.0000

Data Index: 240543 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1248759 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.0713. Min Range: -2.0713

Max Act: 0.9535. Min Act: 0.0000

Data Index: 438449 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0070. Min Act: -0.0000

Data Index: 649563 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.0280. Min Act: -0.0000

Data Index: 914017 (C4 (Web Text))

Max Activating Token Index: 201