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

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

Neuron 308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.1788. Min Act: -0.0000

Data Index: 279648 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1253486 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.0304. Min Act: -0.0000

Data Index: 268237 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.9995. Min Act: -0.0000

Data Index: 1199752 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.9430. Min Act: -0.0000

Data Index: 1141526 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8627. Min Act: -0.0000

Data Index: 77475 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8398. Min Act: -0.0000

Data Index: 786949 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7423. Min Act: -0.0000

Data Index: 132690 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7409. Min Act: -0.0000

Data Index: 651806 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1138941 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1103565 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6462. Min Act: -0.0000

Data Index: 670747 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6713. Min Act: -0.0000

Data Index: 991228 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6593. Min Act: -0.0000

Data Index: 182108 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6404. Min Act: -0.0000

Data Index: 589256 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6155. Min Act: -0.0000

Data Index: 346132 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1064385 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.4994. Min Act: -0.0000

Data Index: 3222 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.5787. Min Act: -0.0000

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.5773. Min Act: -0.0000

Data Index: 787809 (C4 (Web Text))

Max Activating Token Index: 62