Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1865 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.8567. Min Act: -0.0000

Data Index: 699952 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.9963. Min Act: -0.0000

Data Index: 885091 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.8747. Min Act: -0.0000

Data Index: 175611 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1064978 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.8140. Min Act: -0.0000

Data Index: 955652 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6152. Min Act: -0.0000

Data Index: 595371 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6041. Min Act: -0.0000

Data Index: 1043910 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.7334. Min Act: -0.0000

Data Index: 859477 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5938. Min Act: -0.0000

Data Index: 570917 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.7159. Min Act: -0.0000

Data Index: 802122 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.4506. Min Act: -0.0001

Data Index: 536965 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5775. Min Act: -0.0000

Data Index: 554107 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1324885 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5710. Min Act: -0.0000

Data Index: 1242129 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1148826 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6123. Min Act: -0.0000

Data Index: 493817 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.6361. Min Act: -0.0000

Data Index: 49928 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.4988. Min Act: -0.0000

Data Index: 261808 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.5711. Min Act: -0.0000

Data Index: 676303 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.9963. Min Range: -1.9963

Max Act: 1.4412. Min Act: -0.0000

Data Index: 642728 (C4 (Web Text))

Max Activating Token Index: 1021