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

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

Neuron 1008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1831. Min Range: -3.1831

Max Act: 3.1831. Min Act: -0.0000

Data Index: 1065672 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.1831. Min Range: -3.1831

Max Act: 3.0318. Min Act: -0.0000

Data Index: 584614 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.9960. Min Act: -0.0000

Data Index: 803843 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.9588. Min Act: -0.0000

Data Index: 941394 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.9741. Min Act: -0.0000

Data Index: 573029 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.8310. Min Act: -0.0000

Data Index: 1066636 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.9774. Min Act: -0.0000

Data Index: 410822 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.5560. Min Act: -0.0000

Data Index: 258696 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.6426. Min Act: -0.0000

Data Index: 340425 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.2351. Min Act: -0.0000

Data Index: 1259098 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3565. Min Act: -0.0000

Data Index: 920269 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.1883. Min Act: -0.0000

Data Index: 445850 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.1773. Min Act: -0.0000

Data Index: 247820 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3962. Min Act: -0.0000

Data Index: 1293333 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3071. Min Act: -0.0000

Data Index: 220904 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.2941. Min Act: -0.0000

Data Index: 1095336 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3456. Min Act: -0.0000

Data Index: 370974 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3467. Min Act: -0.0000

Data Index: 568888 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.3312. Min Act: -0.0000

Data Index: 611157 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 3.1831. Min Range: -3.1831

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1040346 (C4 (Web Text))

Max Activating Token Index: 291