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

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

Neuron 2273 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1005297 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4493. Min Act: -0.0000

Data Index: 320937 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4470. Min Act: -0.0000

Data Index: 566048 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4309. Min Act: -0.0000

Data Index: 890425 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1258222 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4070. Min Act: -0.0000

Data Index: 707042 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1621122 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3769. Min Act: -0.0000

Data Index: 385540 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4076. Min Act: -0.0000

Data Index: 566728 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3806. Min Act: -0.0000

Data Index: 123819 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3735. Min Act: -0.0000

Data Index: 297700 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1216491 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1274605 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3628. Min Act: -0.0000

Data Index: 257986 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1460794 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3618. Min Act: -0.0000

Data Index: 938770 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1299243 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3539. Min Act: -0.0000

Data Index: 135393 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.3390. Min Act: 0.0000

Data Index: 293295 (C4 (Web Text))

Max Activating Token Index: 1003