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

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

Neuron 2044 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0395. Min Act: -0.0000

Data Index: 165100 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1214. Min Act: -0.0000

Data Index: 1359136 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0875. Min Act: -0.0000

Data Index: 803548 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.7225. Min Act: -0.0000

Data Index: 892453 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.9831. Min Act: -0.0000

Data Index: 870863 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.6813. Min Act: -0.0000

Data Index: 179633 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.8914. Min Act: -0.0000

Data Index: 1277140 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1924. Min Act: -0.0000

Data Index: 596303 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.6926. Min Act: -0.0000

Data Index: 1124129 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.5965. Min Act: -0.0000

Data Index: 294933 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.5809. Min Act: -0.0000

Data Index: 1545838 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.6821. Min Act: -0.0000

Data Index: 1264183 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.4317. Min Act: -0.0000

Data Index: 437383 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.6510. Min Act: -0.0000

Data Index: 406083 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.6160. Min Act: -0.0000

Data Index: 869652 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.4496. Min Act: -0.0000

Data Index: 715486 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1043319 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.5166. Min Act: -0.0000

Data Index: 350592 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.5304. Min Act: -0.0000

Data Index: 552586 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 3.1924. Min Range: -3.1924

Max Act: 2.1348. Min Act: -0.0000

Data Index: 655101 (C4 (Web Text))

Max Activating Token Index: 711