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

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

Neuron 704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8614. Min Act: 0.0000

Data Index: 1184953 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8951. Min Act: -0.0000

Data Index: 295837 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8070. Min Act: -0.0001

Data Index: 596769 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7740. Min Act: -0.0000

Data Index: 271013 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1162948 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7551. Min Act: -0.0000

Data Index: 647455 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7696. Min Act: -0.0000

Data Index: 141321 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7449. Min Act: -0.0000

Data Index: 793560 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1070629 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7362. Min Act: -0.0000

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7687. Min Act: -0.0000

Data Index: 737809 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7675. Min Act: -0.0000

Data Index: 990336 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7593. Min Act: -0.0000

Data Index: 197977 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7381. Min Act: -0.0000

Data Index: 43754 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1209090 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6998. Min Act: -0.0000

Data Index: 348715 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7118. Min Act: -0.0000

Data Index: 70990 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1368423 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6865. Min Act: -0.0000

Data Index: 692870 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6907. Min Act: -0.0000

Data Index: 499299 (C4 (Web Text))

Max Activating Token Index: 215