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

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

Neuron 4413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.2554. Min Act: -0.0000

Data Index: 273820 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1330940 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1307480 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9280. Min Act: -0.0000

Data Index: 571874 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.8388. Min Act: -0.0000

Data Index: 690984 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.8396. Min Act: -0.0000

Data Index: 652639 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.8501. Min Act: -0.0000

Data Index: 417140 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7935. Min Act: -0.0000

Data Index: 918496 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1172396 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7899. Min Act: -0.0000

Data Index: 306812 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7805. Min Act: -0.0000

Data Index: 97485 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7474. Min Act: -0.0000

Data Index: 453095 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7280. Min Act: -0.0000

Data Index: 216183 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7315. Min Act: -0.0000

Data Index: 394374 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7441. Min Act: -0.0000

Data Index: 785270 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1325590 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6824. Min Act: -0.0000

Data Index: 163886 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6839. Min Act: -0.0000

Data Index: 75961 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6471. Min Act: -0.0000

Data Index: 338636 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1294711 (C4 (Web Text))

Max Activating Token Index: 904