Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 333 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8935. Min Act: -0.0000

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7725. Min Act: -0.0001

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7191. Min Act: -0.0000

Data Index: 811551 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6950. Min Act: -0.0000

Data Index: 117730 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6884. Min Act: -0.0000

Data Index: 33370 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7454. Min Act: -0.0000

Data Index: 345548 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6774. Min Act: -0.0000

Data Index: 980019 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1228361 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6807. Min Act: -0.0000

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6831. Min Act: -0.0000

Data Index: 218620 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6503. Min Act: -0.0000

Data Index: 8663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6537. Min Act: -0.0001

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6259. Min Act: -0.0001

Data Index: 140469 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6191. Min Act: -0.0001

Data Index: 45179 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6320. Min Act: -0.0000

Data Index: 974596 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6135. Min Act: -0.0000

Data Index: 686694 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7266. Min Act: -0.0001

Data Index: 1335404 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6267. Min Act: -0.0001

Data Index: 370693 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6370. Min Act: -0.0000

Data Index: 59655 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6367. Min Act: -0.0001

Data Index: 562742 (C4 (Web Text))

Max Activating Token Index: 483